%0 Journal Article %J Information %D 2017 %T Discovering and Understanding City Events with Big Data: The Case of Rome %A Barbara Furletti %A Roberto Trasarti %A Paolo Cintia %A Lorenzo Gabrielli %X The increasing availability of large amounts of data and digital footprints has given rise to ambitious research challenges in many fields, which spans from medical research, financial and commercial world, to people and environmental monitoring. Whereas traditional data sources and census fail in capturing actual and up-to-date behaviors, Big Data integrate the missing knowledge providing useful and hidden information to analysts and decision makers. With this paper, we focus on the identification of city events by analyzing mobile phone data (Call Detail Record), and we study and evaluate the impact of these events over the typical city dynamics. We present an analytical process able to discover, understand and characterize city events from Call Detail Record, designing a distributed computation to implement Sociometer, that is a profiling tool to categorize phone users. The methodology provides an useful tool for city mobility manager to manage the events and taking future decisions on specific classes of users, i.e., residents, commuters and tourists. %B Information %V 8 %P 74 %8 06/2017 %G eng %U https://doi.org/10.3390/info8030074 %R 10.3390/info8030074 %0 Conference Paper %B SEBD - Italian Symposium on Advanced Database Systems %D 2016 %T Big Data and Public Administration: a case study for Tuscany Airports %A Barbara Furletti %A Daniele Fadda %A Leonardo Piccini %A Mirco Nanni %A Patrizia Lattarulo %X In the last decade, the fast development of Information and Communication Technologies led to the wide diffusion of sensors able to track various aspects of human activity, as well as the storage and computational capabilities needed to record and analyze them. The so-called Big Data promise to improve the effectiveness of businesses, the quality of urban life, as well as many other fields, including the functioning of public administrations. Yet, translating the wealth of potential information hidden in Big Data to consumable intelligence seems to be still a difficult task, with a limited basis of success stories. This paper reports a project activity centered on a public administration - IRPET, the Regional Institute for Economic Planning of Tuscany (Italy). The paper deals, among other topics, with human mobility and public transportation at a regional scale, summarizing the open questions posed by the Public Administration (PA), the envisioned role that Big Data might have in answering them, the actual challenges that emerged in trying to implement them, and finally the results we obtained, the limitations that emerged and the lessons learned. %B SEBD - Italian Symposium on Advanced Database Systems %I Matematicamente.it %C Ugento, Lecce (Italy) %8 06/2016 %@ 9788896354889 %G eng %U http://sebd2016.unisalento.it/grid/SEBD2016-proceedings.pdf %0 Journal Article %J Engineering %D 2016 %T Big Data Research in Italy: A Perspective %A Sonia Bergamaschi %A Emanuele Carlini %A Michelangelo Ceci %A Barbara Furletti %A Fosca Giannotti %A Donato Malerba %A Mario Mezzanzanica %A Anna Monreale %A Gabriella Pasi %A Dino Pedreschi %A Raffaele Perego %A Salvatore Ruggieri %X The aim of this article is to synthetically describe the research projects that a selection of Italian universities is undertaking in the context of big data. Far from being exhaustive, this article has the objective of offering a sample of distinct applications that address the issue of managing huge amounts of data in Italy, collected in relation to diverse domains. %B Engineering %V 2 %P 163 %8 06/2016 %G eng %U http://engineering.org.cn/EN/abstract/article_12288.shtml %L 10-1244/N %R 10.1016/J.ENG.2016.02.011 %0 Conference Paper %B IEEE Big Data %D 2015 %T City users’ classification with mobile phone data %A Lorenzo Gabrielli %A Barbara Furletti %A Roberto Trasarti %A Fosca Giannotti %A Dino Pedreschi %X Nowadays mobile phone data are an actual proxy for studying the users’ social life and urban dynamics. In this paper we present the Sociometer, and analytical framework aimed at classifying mobile phone users into behavioral categories by means of their call habits. The analytical process starts from spatio-temporal profiles, learns the different behaviors, and returns annotated profiles. After the description of the methodology and its evaluation, we present an application of the Sociometer for studying city users of one small and one big city, evaluating the impact of big events in these cities. %B IEEE Big Data %C Santa Clara (CA) - USA %8 11/2015 %G eng %0 Conference Paper %B NetMob %D 2015 %T Detecting and understanding big events in big cities %A Barbara Furletti %A Lorenzo Gabrielli %A Roberto Trasarti %A Zbigniew Smoreda %A Maarten Vanhoof %A Cezary Ziemlicki %X Recent studies have shown the great potential of big data such as mobile phone location data to model human behavior. Big data allow to analyze people presence in a territory in a fast and effective way with respect to the classical surveys (diaries or questionnaires). One of the drawbacks of these collection systems is incompleteness of the users' traces; people are localized only when they are using their phones. In this work we define a data mining method for identifying people presence and understanding the impact of big events in big cities. We exploit the ability of the Sociometer for classifying mobile phone users in mobility categories through their presence profile. The experiment in cooperation with Orange Telecom has been conduced in Paris during the event F^ete de la Musique using a privacy preserving protocol. %B NetMob %C Boston %8 04/2015 %G eng %U http://www.netmob.org/assets/img/netmob15_book_of_abstracts_posters.pdf %0 Book Section %B Software Engineering and Formal Methods %D 2015 %T Use of Mobile Phone Data to Estimate Visitors Mobility Flows %A Lorenzo Gabrielli %A Barbara Furletti %A Fosca Giannotti %A Mirco Nanni %A S Rinzivillo %X Big Data originating from the digital breadcrumbs of human activities, sensed as by-product of the technologies that we use for our daily activities, allows us to observe the individual and collective behavior of people at an unprecedented detail. Many dimensions of our social life have big data “proxies”, such as the mobile calls data for mobility. In this paper we investigate to what extent data coming from mobile operators could be a support in producing reliable and timely estimates of intra-city mobility flows. The idea is to define an estimation method based on calling data to characterize the mobility habits of visitors at the level of a single municipality. %B Software Engineering and Formal Methods %I Springer International Publishing %V 8938 %P 214-226 %G eng %U http://link.springer.com/chapter/10.1007%2F978-3-319-15201-1_14 %R 10.1007/978-3-319-15201-1_14 %0 Conference Paper %B EDBT/ICDT 2014 Workshops - Mining Urban Data (MUD) %D 2014 %T Big data analytics for smart mobility: a case study %A Barbara Furletti %A Roberto Trasarti %A Lorenzo Gabrielli %A Mirco Nanni %A Dino Pedreschi %B EDBT/ICDT 2014 Workshops - Mining Urban Data (MUD) %C Athens, Greece %8 03/2014 %U http://ceur-ws.org/Vol-1133/paper-57.pdf %M ISSN - 1613-0073 %0 Journal Article %J Telecommunications Policy %D 2014 %T Discovering urban and country dynamics from mobile phone data with spatial correlation patterns %A Roberto Trasarti %A Ana-Maria Olteanu-Raimond %A Mirco Nanni %A Thomas Couronné %A Barbara Furletti %A Fosca Giannotti %A Zbigniew Smoreda %A Cezary Ziemlicki %K Urban dynamics %X Abstract Mobile communication technologies pervade our society and existing wireless networks are able to sense the movement of people, generating large volumes of data related to human activities, such as mobile phone call records. At the present, this kind of data is collected and stored by telecom operators infrastructures mainly for billing reasons, yet it represents a major source of information in the study of human mobility. In this paper, we propose an analytical process aimed at extracting interconnections between different areas of the city that emerge from highly correlated temporal variations of population local densities. To accomplish this objective, we propose a process based on two analytical tools: (i) a method to estimate the presence of people in different geographical areas; and (ii) a method to extract time- and space-constrained sequential patterns capable to capture correlations among geographical areas in terms of significant co-variations of the estimated presence. The methods are presented and combined in order to deal with two real scenarios of different spatial scale: the Paris Region and the whole France. %B Telecommunications Policy %P - %U http://www.sciencedirect.com/science/article/pii/S0308596113002012 %R http://dx.doi.org/10.1016/j.telpol.2013.12.002 %0 Book Section %B Data Science and Simulation in Transportation Research %D 2014 %T Mobility Profiling %A Mirco Nanni %A Roberto Trasarti %A Paolo Cintia %A Barbara Furletti %A Chiara Renso %A Lorenzo Gabrielli %A S Rinzivillo %A Fosca Giannotti %X The ability to understand the dynamics of human mobility is crucial for tasks like urban planning and transportation management. The recent rapidly growing availability of large spatio-temporal datasets gives us the possibility to develop sophisticated and accurate analysis methods and algorithms that can enable us to explore several relevant mobility phenomena: the distinct access paths to a territory, the groups of persons that move together in space and time, the regions of a territory that contains a high density of traffic demand, etc. All these paradigmatic perspectives focus on a collective view of the mobility where the interesting phenomenon is the result of the contribution of several moving objects. In this chapter, the authors explore a different approach to the topic and focus on the analysis and understanding of relevant individual mobility habits in order to assign a profile to an individual on the basis of his/her mobility. This process adds a semantic level to the raw mobility data, enabling further analyses that require a deeper understanding of the data itself. The studies described in this chapter are based on two large datasets of spatio-temporal data, originated, respectively, from GPS-equipped devices and from a mobile phone network. %B Data Science and Simulation in Transportation Research %I IGI Global %P 1-29 %& 1 %R 10.4018/978-1-4666-4920-0.ch001 %0 Conference Paper %B 47th SIS Scientific Meeting of the Italian Statistica Society %D 2014 %T Use of mobile phone data to estimate mobility flows. Measuring urban population and inter-city mobility using big data in an integrated approach %A Barbara Furletti %A Lorenzo Gabrielli %A Fosca Giannotti %A Letizia Milli %A Mirco Nanni %A Dino Pedreschi %? Roberta Vivio %? Giuseppe Garofalo %X The Big Data, originating from the digital breadcrumbs of human activi- ties, sensed as a by-product of the technologies that we use for our daily activities, let us to observe the individual and collective behavior of people at an unprecedented detail. Many dimensions of our social life have big data “proxies”, as the mobile calls data for mobility. In this paper we investigate to what extent such ”big data”, in integration with administrative ones, could be a support in producing reliable and timely estimates of inter-city mobility. The study has been jointly developed by Is- tat, CNR, University of Pisa in the range of interest of the “Commssione di studio avente il compito di orientare le scelte dellIstat sul tema dei Big Data ”. In an on- going project at ISTAT, called “Persons and Places” – based on an integration of administrative data sources, it has been produced a first release of Origin Destina- tion matrix – at municipality level – assuming that the places of residence and that of work (or study) be the terminal points of usual individual mobility for work or study. The coincidence between the city of residence and that of work (or study) – is considered as a proxy of the absence of intercity mobility for a person (we define him a static resident). The opposite case is considered as a proxy of presence of mo- bility (the person is a dynamic resident: commuter or embedded). As administrative data do not contain information on frequency of the mobility, the idea is to specify an estimate method, using calling data as support, to define for each municipality the stock of standing residents, embedded city users and daily city users (commuters) %B 47th SIS Scientific Meeting of the Italian Statistica Society %C Cagliari %8 06/2014 %@ 978-88-8467-874-4 %U http://www.sis2014.it/proceedings/allpapers/3026.pdf %0 Conference Paper %B Proceedings of MoKMaSD %D 2014 %T Use of mobile phone data to estimate visitors mobility flows %A Lorenzo Gabrielli %A Barbara Furletti %A Fosca Giannotti %A Mirco Nanni %A S Rinzivillo %X Big Data originating from the digital breadcrumbs of human activities, sensed as by-product of the technologies that we use for our daily activities, allows us to observe the individual and collective behavior of people at an unprecedented detail. Many dimensions of our social life have big data “proxies”, such as the mo- bile calls data for mobility. In this paper we investigate to what extent data coming from mobile operators could be a support in producing reliable and timely estimates of intra-city mobility flows. The idea is to define an estimation method based on calling data to characterize the mobility habits of visitors at the level of a single municipality %B Proceedings of MoKMaSD %U http://www.di.unipi.it/mokmasd/symposium-2014/preproceedings/GabrielliEtAl-mokmasd2014.pdf %0 Conference Proceedings %B IEEE Big Data %D 2013 %T Analysis of GSM Calls Data for Understanding User Mobility Behavior %A Barbara Furletti %A Lorenzo Gabrielli %A Chiara Renso %A S Rinzivillo %B IEEE Big Data %C Santa Clara, California %0 Conference Paper %B Workshop at KDD 2013 %D 2013 %T Inferring human activities from GPS tracks UrbComp %A Paolo Cintia %A Barbara Furletti %A Chiara Renso %B Workshop at KDD 2013 %C Chicago USA %0 Conference Paper %B In D4D Challenge @ 3rd Conf. on the Analysis of Mobile Phone datasets (NetMob 2013) %D 2013 %T MP4-A Project: Mobility Planning For Africa %A Mirco Nanni %A Roberto Trasarti %A Barbara Furletti %A Lorenzo Gabrielli %A Peter Van Der Mede %A Joost De Bruijn %A Erik de Romph %A Gerard Bruil %X This project aims to create a tool that uses mobile phone transaction (trajectory) data that will be able to address transportation related challenges, thus allowing promotion and facilitation of sustainable urban mobility planning in Third World countries. The proposed tool is a transport demand model for Ivory Coast, with emphasis on its major urbanization Abidjan. The consortium will bring together available data from the internet, and integrate these with the mobility data obtained from the mobile phones in order to build the best possible transport model. A transport model allows an understanding of current and future infrastructure requirements in Ivory Coast. As such, this project will provide the first proof of concept. In this context, long-term analysis of individual call traces will be performed to reconstruct systematic movements, and to infer an origin-destination matrix. A similar process will be performed using the locations of caller and recipient of phone calls, enabling the comparison of socio-economic ties vs. mobility. The emerging links between different areas will be used to build an effective map to optimize regional border definitions and road infrastructure from a mobility perspective. Finally, we will try to build specialized origin-destination matrices for specific categories of population. Such categories will be inferred from data through analysis of calling behaviours, and will also be used to characterize the population of different cities. The project also includes a study of data compliance with distributions of standard measures observed in literature, including distribution of calls, call durations and call network features. %B In D4D Challenge @ 3rd Conf. on the Analysis of Mobile Phone datasets (NetMob 2013) %C Cambridge, USA %G eng %U http://perso.uclouvain.be/vincent.blondel/netmob/2013/D4D-book.pdf %0 Conference Paper %B NetMob Conference 2013 %D 2013 %T Pisa Tourism fluxes Observatory: deriving mobility indicators from GSM call habits %A Barbara Furletti %A Lorenzo Gabrielli %A Chiara Renso %A S Rinzivillo %B NetMob Conference 2013 %0 Conference Paper %B Citizen in Sensor Networks - Second International Workshop, CitiSens 2013, Barcelona, Spain, September 19, 2013, Revised Selected Papers %D 2013 %T Transportation Planning Based on {GSM} Traces: {A} Case Study on Ivory Coast %A Mirco Nanni %A Roberto Trasarti %A Barbara Furletti %A Lorenzo Gabrielli %A Peter Van Der Mede %A Joost De Bruijn %A Erik de Romph %A Gerard Bruil %B Citizen in Sensor Networks - Second International Workshop, CitiSens 2013, Barcelona, Spain, September 19, 2013, Revised Selected Papers %G eng %U http://dx.doi.org/10.1007/978-3-319-04178-0_2 %R 10.1007/978-3-319-04178-0_2 %0 Report %D 2012 %T Analisi di Mobilita' con dati eterogenei %A Barbara Furletti %A Roberto Trasarti %A Lorenzo Gabrielli %A S Rinzivillo %A Luca Pappalardo %A Fosca Giannotti %I ISTI - CNR %C Pisa %0 Conference Paper %B ACM SIGKDD International Workshop on Urban Computing %D 2012 %T Identifying users profiles from mobile calls habits %A Barbara Furletti %A Lorenzo Gabrielli %A Chiara Renso %A S Rinzivillo %X The huge quantity of positioning data registered by our mobile phones stimulates several research questions, mainly originating from the combination of this huge quantity of data with the extreme heterogeneity of the tracked user and the low granularity of the data. We propose a methodology to partition the users tracked by GSM phone calls into profiles like resident, commuters, in transit and tourists. The methodology analyses the phone calls with a combination of top-down and bottom up techniques where the top-down phase is based on a sequence of queries that identify some behaviors. The bottom-up is a machine learning phase to find groups of similar call behavior, thus refining the previous step. The integration of the two steps results in the partitioning of mobile traces into these four user categories that can be deeper analyzed, for example to understand the tourist movements in city or the traffic effects of commuters. An experiment on the identification of user profiles on a real dataset collecting call records from one month in the city of Pisa illustrates the methodology. %B ACM SIGKDD International Workshop on Urban Computing %I ACM New York, NY, USA ©2012 %C Beijing, China %@ 978-1-4503-1542-5 %U http://delivery.acm.org/10.1145/2350000/2346500/p17-furletti.pdf?ip=146.48.83.121&acc=ACTIVE%20SERVICE&CFID=166768290&CFTOKEN=58719386&__acm__=1357648050_e23771c2f6bd8feb96bd66b39294175d %R 10.1145/2346496.2346500 %0 Journal Article %J Intelligent Data Analysis %D 2012 %T Knowledge Discovery in Ontologies %A Barbara Furletti %A Franco Turini %B Intelligent Data Analysis %V 16 %U http://iospress.metapress.com/content/765h53w41286p578/fulltext.pdf %& 513 %R 10.3233/IDA-2012-0536 %0 Book Section %B Software and Data Technologies %D 2012 %T What else can be extracted from ontologies? Influence Rules %A Franco Turini %A Barbara Furletti %B Software and Data Technologies %S Communications in Computer and Information Science %I Springer %0 Conference Paper %B International Conference on Software and Data Technologies (ICSOFT) %D 2011 %T Mining Influence Rules out of Ontologies %A Barbara Furletti %A Franco Turini %B International Conference on Software and Data Technologies (ICSOFT) %C Siviglia, Spagna %8 2011 %0 Journal Article %J Quality Technology & Quantitative Management %D 2010 %T Improving the Business Plan Evaluation Process: the Role of Intangibles %A Barbara Furletti %A Franco Turini %A Andrea Bellandi %A Miriam Baglioni %A Chiara Pratesi %B Quality Technology & Quantitative Management %V 7 %8 2010 %U http://web.it.nctu.edu.tw/~qtqm/upcomingpapers/2010V7N1/2010V7N1_F3.pdf %& 35 %0 Thesis %B IMT - Lucca %D 2009 %T Ontology Driven Knowledge Discovery %A Barbara Furletti %B IMT - Lucca %I IMT - Lucca %C Lucca - Italy %0 Book Section %B Advances in Robotics, Automation and Control %D 2008 %T Discovering Strategic Behaviour in Multi- Agent Scenarios by Ontology-Driven Mining %A Davide Bacciu %A Andrea Bellandi %A Barbara Furletti %A Valerio Grossi %A Andrea Romei %B Advances in Robotics, Automation and Control %@ 978-953-7619-16-9 %U http://www.intechopen.com/books/advances_in_robotics_automation_and_control/discovering_strategic_behaviors_in_multi-agent_scenarios_by_ontology-driven_mining %0 Conference Paper %B IADIS International Conference Applied Computing %D 2008 %T AN EXTENSIBLE AND INTERACTIVE SOFTWARE AGENT FOR MOBILE DEVICES BASED ON GPS DATA %A Barbara Furletti %A Francesco Fornasari %A Claudio Montanari %B IADIS International Conference Applied Computing %8 2008 %@ 978-972-8924-56-0 %U http://www.iadisportal.org/digital-library/mdownload/an-extensible-and-interactive-software-agent-for-mobile-devices-based-on-gps-data %0 Conference Paper %B IASTED International Conference on Artificial Intelligence and Applications (AIA) %D 2008 %T Ontological Support for Association Rule Mining %A Barbara Furletti %A Andrea Bellandi %A Valerio Grossi %A Andrea Romei %B IASTED International Conference on Artificial Intelligence and Applications (AIA) %C Innsbruck, Austria %0 Conference Paper %B EDOC %D 2008 %T Ontology-Based Business Plan Classification %A Miriam Baglioni %A Andrea Bellandi %A Barbara Furletti %A Laura Spinsanti %A Franco Turini %B EDOC %P 365-371 %0 Conference Paper %B Enterprise Distributed Object Computing Conference (EDOC) %D 2008 %T Ontology-Based Business Plan Classification %A Franco Turini %A Barbara Furletti %A Miriam Baglioni %A Laura Spinsanti %A Andrea Bellandi %B Enterprise Distributed Object Computing Conference (EDOC) %8 2008 %@ 978-0-7695-3373-5 %U http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4634789 %R http://dx.doi.org/10.1109/EDOC.2008.30 %0 Conference Paper %B International Workshop on Contexts and Ontologies: Representation and Reasoning %D 2007 %T Ontology-Driven Association Rule Extraction: A Case Study %A Barbara Furletti %A Andrea Bellandi %A Valerio Grossi %A Andrea Romei %B International Workshop on Contexts and Ontologies: Representation and Reasoning %C Roskilde, Denmark %8 2007 %U http://ceur-ws.org/Vol-298/paper1.pdf %0 Conference Paper %B IADIS International Conference WWW/Internet 2007 %D 2007 %T PUSHING CONSTRAINTS IN ASSOCIATION RULE MINING: AN ONTOLOGY-BASED APPROACH %A Barbara Furletti %A Andrea Bellandi %A Andrea Romei %A Valerio Grossi %B IADIS International Conference WWW/Internet 2007 %8 2007 %@ 978-972-8924-44-7 %U http://www.iadisportal.org/digital-library/mdownload/pushing-constraints-in-association-rule-mining-an-ontology-based-approach %0 Conference Paper %B Reasoning, Action and Interaction in AI Theories and Systems %D 2006 %T Examples of Integration of Induction and Deduction in Knowledge Discovery %A Franco Turini %A Miriam Baglioni %A Barbara Furletti %A S Rinzivillo %B Reasoning, Action and Interaction in AI Theories and Systems %P 307-326 %0 Book Section %B Reasoning, Action and Interaction in AI Theories and Systems %D 2006 %T Examples of Integration of Induction and Deduction in Knowledge Discovery %A Franco Turini %A Miriam Baglioni %A Barbara Furletti %A S Rinzivillo %B Reasoning, Action and Interaction in AI Theories and Systems %S LNAI %V 4155 %P 307-326 %U http://www.springerlink.com/content/m400v4507476n18g/fulltext.pdf %R 10.1007/11829263_17 %0 Conference Paper %B IADIS International Conference Applied Computing 2006 %D 2006 %T A Tool for Economic Plans analysis based on expert knowledge and data mining techniques %A Miriam Baglioni %A Barbara Furletti %A Franco Turini %B IADIS International Conference Applied Computing 2006 %8 2006 %@ 972-8924-09-7 %U http://www.iadisportal.org/digital-library/mdownload/a-tool-for-economic-plans-analysis-based-on-expert-knowledge-and-data-mining-techniques %0 Conference Paper %B ACM Symposium on Applied Computing %D 2005 %T DrC4.5: Improving C4.5 by means of Prior Knowledge %A Miriam Baglioni %A Barbara Furletti %A Franco Turini %B ACM Symposium on Applied Computing %I ACM %C Santa Fe, New Mexico, USA %@ 1-58113-964-0 %U http://dl.acm.org/ft_gateway.cfm?id=1066787&ftid=311609&dwn=1&CFID=96873366&CFTOKEN=59233511 %R http://dx.doi.org/10.1145/1066677.1066787