The purpose of the course is to introduce the main analysis techniques for spatio-temporal data, with a particular focus on human mobility (including vehicles), aimed to better understand the overall mobility of a territory. The presentation will be supported by several case studies developed with the SoBigData.eu laboratory.
The module aims to teach how to present the knowledge extracted from big data using multimedia story telling. It also shows some of the most recent and meaningful experiences of journalism and story telling based on quantitative information extracted from different data sources.
Born in Salerno (Italy), I earned my PhD in Computer Science at University of Pisa with the thesis "Human Mobility, Social Networks and Economic Development: a Data Science perspective". In my research, I exploit the power of Big Data to study many aspects of human behavior: the patterns of human mobility, the structure and evolution of complex networks, the patterns of success in sports, and the usage of data-driven measures of human behavior to monitor and predict the economic development of countries, cities, and territories.
Angelica Lo Duca is a postdoctoral researcher at the Institute of Informatics and Telematics of the National Research Council of Pisa. In 2012, she received her Ph.D. in Ingegneria dell'Informazione from the University of Pisa. She received her Bachelor's and Master's degrees in Computer Engineering from University of Pisa respectively in 2005 and 2007. Currently, she works at the Web Applications for the Future Internet Laboratory, in the Semantic Web and Data Visualization group.
The module presents technologies and systems for designing, populating and querying Data Warehouse for decision support. The emphasis is on technologies and analysis of application problems by using examples and case studies. The student will acquire knowledge and skills on major technologies for Business Intelligence such as ETL (Extract, Transform and Load), Data Warehousing, Analytics SQL, OLAP (Online Analytical Processing).
The module aims to present the basic methods and techniques for the visualization and presentation of the information obtained from different sources: structured data (relational, hierarchical, trees), network data (social network), temporal data, spatial data and spatio-temporal data. Studying the existing methods and tools, some scenarios of visual analytics will be presented.
Born and raised in Viareggio, Tuscany, Roberto Pellungrini is a PhD student in Computer Science at the University of Pisa. His main research interests concern ethical aspects related to Data Science, in particular regarding Privacy issues. Before winning the PhD scholarship, he attained a Master Degree in Business Informatics with a thesis on Assessing Privacy Risk and Quality in Human Mobility Data.
He graduated cum laude in 2016 in Computer Science at the University of Pisa (Italy), then he started in the same year the PhD in Computer Science at the same university. Roberto is currently a PhD student and a member of the High Performance Computing laboratory (HPC Lab) at the ISTI "A. Faedo" institute of CNR (Pisa). His main research interests are Information Retrieval, Machine Learning and Web Mining.
Alejandro Moreo Fernández received a PhD in Computer Sciences and Information Technologies from the University of Granada in 2013. He is a Postdoctoral Fellow at Istituto di Scienza e Tecnologie dell'Informazione ``A. Faedo'', which is part of the National Research Council (CNR). His research interests include deep learning and representation learning, with particular focus on imbalanced text classification, multilingual text classification, and cross-domain and cross-lingual sentiment classification.
The internship period is 500 hours, 20 CFU, that single student or a small group of students have to spend in one of the companies and institutions partner of the master, working on an agreed project and under the supervision of a team of tutors composed by the teachers of the master and the management companies.
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |