2019
Journal article
Open Access
Dissecting global air traffic data to discern different types and trends of transnational human mobility
Gabrielli L, Deutschmann E, Natale F, Recchi E, Vespe M
Human mobility across national borders is a key phenomenon of our time. At the global scale, however, we still know relatively little about the structure and nature of such transnational movements. This study uses a large dataset on monthly air passenger traffic between 239 countries worldwide from 2010 to 2018 to gain new insights into (a) mobility trends over time and (b) types of mobility. A time series decomposition is used to extract a trend and a seasonal component. The trend component permits--at a higher level of granularity than previous sources--to examine the development of mobility between countries and to test how it is affected by policy and infrastructural changes, economic developments, and violent conflict. The seasonal component allows, by measuring the lag between initial and return motion, to discern different types of mobility, from tourism to seasonal work migration. Moreover, the exact shape of seasonal mobility patterns is extracted, allowing to identify regular mobility peaks and nadirs throughout the year. The result is a unique classification of trends and types of mobility for a global set of country pairs. A range of implications and possible applications are discussed.Source: EPJ DATA SCIENCE, vol. 8, pp. 1-24
DOI: 10.1140/epjds/s13688-019-0204-x
Metrics:
Gabrielli L, Deutschmann E, Natale F, Recchi E, Vespe M
Human mobility across national borders is a key phenomenon of our time. At the global scale, however, we still know relatively little about the structure and nature of such transnational movements. This study uses a large dataset on monthly air passenger traffic between 239 countries worldwide from 2010 to 2018 to gain new insights into (a) mobility trends over time and (b) types of mobility. A time series decomposition is used to extract a trend and a seasonal component. The trend component permits--at a higher level of granularity than previous sources--to examine the development of mobility between countries and to test how it is affected by policy and infrastructural changes, economic developments, and violent conflict. The seasonal component allows, by measuring the lag between initial and return motion, to discern different types of mobility, from tourism to seasonal work migration. Moreover, the exact shape of seasonal mobility patterns is extracted, allowing to identify regular mobility peaks and nadirs throughout the year. The result is a unique classification of trends and types of mobility for a global set of country pairs. A range of implications and possible applications are discussed.Source: EPJ DATA SCIENCE, vol. 8, pp. 1-24
DOI: 10.1140/epjds/s13688-019-0204-x
Metrics:
See at:
EPJ Data Science 
| epjdatascience.springeropen.com | EPJ Data Science | CNR IRIS | ISTI Repository | CNR IRIS 
2022
Journal article
Open Access
Did exposure to asylum seeking migration affect the electoral outcome of the 'Alternative für Deutschland' in Berlin? Evidence from the 2019 european elections
Pettrachin A, Gabrielli L, Kim J, Ludwigdehm S, Potzschke S
This article analyses the impact of exposure to asylum-seeking migration during the European 'refugee crisis' on votes for the far-right Alternative für Deutschland at the 2019 European elections in Berlin. While other scholars investigated the relationship between locals' exposure to asylum-seekers and far-right voting, we analyse this relationship at a very small scale (electoral district level), adopting an innovative methodological approach, based on geo-localization techniques and high-resolution spatial statistics. Furthermore, we assess the impact on this relationship of some previously neglected variables. Through spatial regression models, we show that exposure to asylum-seeking migration is negatively correlated with AfD vote shares, which provides support for so-called 'contact theory' and that the relationship is stronger in better-off districts. Remarkably, the relationship is weaker in districts containing bigger reception centres, which suggests that the effects of asylum-seeking migration depend on the perceived contact intensity (and, therefore, a moderating effect of reception centre size). Finally, the effects of districts' socio-economic deprivation on the relationship between exposure to asylum-seeking migration and AfD vote shares is different in districts located in former East and West Berlin, which suggests an effect of socio-cultural history on the relationship between exposure to migration and far-right voting.Source: JOURNAL OF ETHNIC AND MIGRATION STUDIES
DOI: 10.1080/1369183x.2022.2100543
Metrics:
Pettrachin A, Gabrielli L, Kim J, Ludwigdehm S, Potzschke S
This article analyses the impact of exposure to asylum-seeking migration during the European 'refugee crisis' on votes for the far-right Alternative für Deutschland at the 2019 European elections in Berlin. While other scholars investigated the relationship between locals' exposure to asylum-seekers and far-right voting, we analyse this relationship at a very small scale (electoral district level), adopting an innovative methodological approach, based on geo-localization techniques and high-resolution spatial statistics. Furthermore, we assess the impact on this relationship of some previously neglected variables. Through spatial regression models, we show that exposure to asylum-seeking migration is negatively correlated with AfD vote shares, which provides support for so-called 'contact theory' and that the relationship is stronger in better-off districts. Remarkably, the relationship is weaker in districts containing bigger reception centres, which suggests that the effects of asylum-seeking migration depend on the perceived contact intensity (and, therefore, a moderating effect of reception centre size). Finally, the effects of districts' socio-economic deprivation on the relationship between exposure to asylum-seeking migration and AfD vote shares is different in districts located in former East and West Berlin, which suggests an effect of socio-cultural history on the relationship between exposure to migration and far-right voting.Source: JOURNAL OF ETHNIC AND MIGRATION STUDIES
DOI: 10.1080/1369183x.2022.2100543
Metrics:
See at:
CNR IRIS | ISTI Repository | www.tandfonline.com | CNR IRIS
2023
Journal article
Open Access
Roads, rails, and checkpoints: assessing the permeability of nation-state borders worldwide
Deutschmann E, Gabrielli L, Recchi E
The permeability of nation-state borders determines the flow of people and commodities between countries and therefore greatly influences many aspects of human development from trade and economic inequality to migration and the ethnic composition of societies worldwide. While past research on the topic has focused on border fortification (walls, fences, etc.) or the legal dimension of border controls, we take a different approach by arguing that transport infrastructure (paths, roads, railroads, ferries) together with political checkpoints can be used as valuable indicators for the permeability of borders worldwide. More and better transport infrastructure increases permeability, whereas checkpoints create the political capacity for reducing entries. Using automatized computational methods combined with extensive manual checks, we parse data from OpenStreetMap and the World Food Programme to detect cross-border transport infrastructure and checkpoints. Based on this information, we define an index of border permeability for 312 land borders globally. Subsequent analyses show that regardless of the degree of closure enforcement at checkpoints, Europe and Africa have the most, and the Americas the least, permeable borders worldwide. Regression models reveal that border permeability is higher in densely populated areas and that economic development, by far the most relevant explanatory factor, has a curvilinear relationship with border permeability: Borders of very rich and very poor countries are highly permeable, whereas those of moderately prosperous nation-states are significantly harder to cross. Implications of this remarkably clear pattern are discussed.Source: WORLD DEVELOPMENT, vol. 164 (issue 106175)
DOI: 10.1016/j.worlddev.2022.106175
Metrics:
Deutschmann E, Gabrielli L, Recchi E
The permeability of nation-state borders determines the flow of people and commodities between countries and therefore greatly influences many aspects of human development from trade and economic inequality to migration and the ethnic composition of societies worldwide. While past research on the topic has focused on border fortification (walls, fences, etc.) or the legal dimension of border controls, we take a different approach by arguing that transport infrastructure (paths, roads, railroads, ferries) together with political checkpoints can be used as valuable indicators for the permeability of borders worldwide. More and better transport infrastructure increases permeability, whereas checkpoints create the political capacity for reducing entries. Using automatized computational methods combined with extensive manual checks, we parse data from OpenStreetMap and the World Food Programme to detect cross-border transport infrastructure and checkpoints. Based on this information, we define an index of border permeability for 312 land borders globally. Subsequent analyses show that regardless of the degree of closure enforcement at checkpoints, Europe and Africa have the most, and the Americas the least, permeable borders worldwide. Regression models reveal that border permeability is higher in densely populated areas and that economic development, by far the most relevant explanatory factor, has a curvilinear relationship with border permeability: Borders of very rich and very poor countries are highly permeable, whereas those of moderately prosperous nation-states are significantly harder to cross. Implications of this remarkably clear pattern are discussed.Source: WORLD DEVELOPMENT, vol. 164 (issue 106175)
DOI: 10.1016/j.worlddev.2022.106175
Metrics:
See at:
World Development | CNR IRIS | ISTI Repository | www.sciencedirect.com | CNR IRIS
2018
Other
Metadata Only Access
Towards big data methods and technologies for official statistics
Lorenzo Gabrielli
This thesis aims to demonstrate in a tangible way how mobile phone data, private vehicle tracks, and scanner data are useful for measuring complex systems. The three main areas of application concerned use of Big Data: i) for measuring the presence within a territory through Data Mining techniques, ii) to now-casting socio-economic development of a country, and iii) for measuring the dynamics of cities. First, it has been developed a tool for real-time demography demonstrating how to use mobile phone data over a wide area to achieve a new Official Statistic indicators. The study showed how Big Data, either using mobile phone data or scanner data are useful and effective for carrying out a continuous census of the population. Second, it has been proposed an analytical framework able to evaluate relations between relevant aspects of human behavior and the well-being of a territory. We found out that the diversity of human mobility is a mirror of some aspects of socio-economic development and well-being. Then, we showed how mobility features help to improve the performance of state-of-the-art methodology such as small area estimation methodologies. Finally, it has been analyzed how mobility interacts with the territory due to the movement of people. We proposed to use mobile phone data and GPS tracks for city government measuring the attractiveness of cities. Furthermore, a data analysis approach aimed to identify mobility functional areas in a completely data-driven way has been proposed. The main findings of the thesis concern the statistical and ethical evaluation of results with official sources and showed that methodologies could be applied in other contexts and with different data sources as well. We showed how the geographic information contained in the data sources is incredibly useful to observe our society with a new microscope. Thanks to the opportunity provided by the varied scientific context of SoBigData, the European Research Infrastructure for Big Data and Social Mining. the Ph.D. also contributed to develop and promote responsible data science because the ethical framework is considered as part of the CRISP model, not a problem to treat apart.Project(s): SoBigData
Lorenzo Gabrielli
This thesis aims to demonstrate in a tangible way how mobile phone data, private vehicle tracks, and scanner data are useful for measuring complex systems. The three main areas of application concerned use of Big Data: i) for measuring the presence within a territory through Data Mining techniques, ii) to now-casting socio-economic development of a country, and iii) for measuring the dynamics of cities. First, it has been developed a tool for real-time demography demonstrating how to use mobile phone data over a wide area to achieve a new Official Statistic indicators. The study showed how Big Data, either using mobile phone data or scanner data are useful and effective for carrying out a continuous census of the population. Second, it has been proposed an analytical framework able to evaluate relations between relevant aspects of human behavior and the well-being of a territory. We found out that the diversity of human mobility is a mirror of some aspects of socio-economic development and well-being. Then, we showed how mobility features help to improve the performance of state-of-the-art methodology such as small area estimation methodologies. Finally, it has been analyzed how mobility interacts with the territory due to the movement of people. We proposed to use mobile phone data and GPS tracks for city government measuring the attractiveness of cities. Furthermore, a data analysis approach aimed to identify mobility functional areas in a completely data-driven way has been proposed. The main findings of the thesis concern the statistical and ethical evaluation of results with official sources and showed that methodologies could be applied in other contexts and with different data sources as well. We showed how the geographic information contained in the data sources is incredibly useful to observe our society with a new microscope. Thanks to the opportunity provided by the varied scientific context of SoBigData, the European Research Infrastructure for Big Data and Social Mining. the Ph.D. also contributed to develop and promote responsible data science because the ethical framework is considered as part of the CRISP model, not a problem to treat apart.Project(s): SoBigData
See at:
etd.adm.unipi.it | CNR IRIS
2014
Contribution to book
Restricted
From tweets to semantic trajectories: mining anomalous urban mobility patterns
Gabrielli L, Rinzivillo S, Ronzano F, Villatoro D
This paper proposes and experiments new techniques to detect urban mobility patterns and anomalies by analyzing trajectories mined from publicly available geo-positioned social media traces left by the citizens (namely Twitter). By collecting a large set of geo-located tweets characterizing a specific urban area over time, we semantically enrich the available tweets with information about its author - i.e. a res- ident or a tourist - and the purpose of the movement - i.e. the activity performed in each place. We exploit mobility data mining techniques together with social net- work analysis methods to aggregate similar trajectories thus pointing out hot spots of activities and flows of people together with their varia- tions over time. We apply and validate the proposed trajectory mining approaches to a large set of trajectories built from the geo-positioned tweets gathered in Barcelona during the Mobile World Congress 2012 (MWC2012), one of the greatest events that affected the city in 2012.DOI: 10.1007/978-3-319-04178-0_3
Project(s): DATA SIM
Metrics:
Gabrielli L, Rinzivillo S, Ronzano F, Villatoro D
This paper proposes and experiments new techniques to detect urban mobility patterns and anomalies by analyzing trajectories mined from publicly available geo-positioned social media traces left by the citizens (namely Twitter). By collecting a large set of geo-located tweets characterizing a specific urban area over time, we semantically enrich the available tweets with information about its author - i.e. a res- ident or a tourist - and the purpose of the movement - i.e. the activity performed in each place. We exploit mobility data mining techniques together with social net- work analysis methods to aggregate similar trajectories thus pointing out hot spots of activities and flows of people together with their varia- tions over time. We apply and validate the proposed trajectory mining approaches to a large set of trajectories built from the geo-positioned tweets gathered in Barcelona during the Mobile World Congress 2012 (MWC2012), one of the greatest events that affected the city in 2012.DOI: 10.1007/978-3-319-04178-0_3
Project(s): DATA SIM
Metrics:
See at:
doi.org | CNR IRIS | CNR IRIS | link.springer.com
2018
Conference article
Open Access
Recognizing Residents and Tourists with Retail Data Using Shopping Profiles
Guidotti R, Gabrielli L
The huge quantity of personal data stored by service providers registering customers daily life enables the analysis of individual findgerprints characterizing the customers' behavioral profiles. We propose a framework for recognizing residents, tourists and occasional shoppers among the customers of a retail market chain. We employ our recognition framework on a real massive dataset containing the shopping transactions of more than one million of customers, and we identify representative temporal shopping profiles for residents, tourists and occasional customers. Our experiments show that even though residents are about 33% of the customers they are responsible for more than 90% of the expenditure. We statistically validate the number of residents and tourists with national official statistics enabling in this way the adoption of our recognition framework for the development of novel services and analysis.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING, pp. 353-363. Pisa, Italy, 29-30/11/2017
DOI: 10.1007/978-3-319-76111-4_35
Project(s): SoBigData
Metrics:
Guidotti R, Gabrielli L
The huge quantity of personal data stored by service providers registering customers daily life enables the analysis of individual findgerprints characterizing the customers' behavioral profiles. We propose a framework for recognizing residents, tourists and occasional shoppers among the customers of a retail market chain. We employ our recognition framework on a real massive dataset containing the shopping transactions of more than one million of customers, and we identify representative temporal shopping profiles for residents, tourists and occasional customers. Our experiments show that even though residents are about 33% of the customers they are responsible for more than 90% of the expenditure. We statistically validate the number of residents and tourists with national official statistics enabling in this way the adoption of our recognition framework for the development of novel services and analysis.Source: LECTURE NOTES OF THE INSTITUTE FOR COMPUTER SCIENCES, SOCIAL INFORMATICS AND TELECOMMUNICATIONS ENGINEERING, pp. 353-363. Pisa, Italy, 29-30/11/2017
DOI: 10.1007/978-3-319-76111-4_35
Project(s): SoBigData
Metrics:
See at:
CNR IRIS | link.springer.com | ISTI Repository | Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering | CNR IRIS
2018
Journal article
Open Access
Gravity and scaling laws of city to city migration
Prieto Curiel R, Pappalardo L, Gabrielli L, Bishop S R
Models of human migration provide powerful tools to forecast the flow of migrants, measure the impact of a policy, determine the cost of physical and political frictions and more. Here, we analyse the migration of individuals from and to cities in the US, finding that city to city migration follows scaling laws, so that the city size is a significant factor in determining whether, or not, an individual decides to migrate and the city size of both the origin and destination play key roles in the selection of the destination. We observe that individuals from small cities tend to migrate more frequently, tending to move to similar-sized cities, whereas individuals from large cities do not migrate so often, but when they do, they tend to move to other large cities. Building upon these findings we develop a scaling model which describes internal migration as a two-step decision process, demonstrating that it can partially explain migration fluxes based solely on city size. We then consider the impact of distance and construct a gravity-scaling model by combining the observed scaling patterns with the gravity law of migration. Results show that the scaling laws are a significant feature of human migration and that the inclusion of scaling can overcome the limits of the gravity and the radiation models of human migration.Source: PLOS ONE, vol. 13 (issue 7), pp. 1-19
DOI: 10.1371/journal.pone.0199892
Project(s): CIMPLEX, SoBigData
Metrics:
Prieto Curiel R, Pappalardo L, Gabrielli L, Bishop S R
Models of human migration provide powerful tools to forecast the flow of migrants, measure the impact of a policy, determine the cost of physical and political frictions and more. Here, we analyse the migration of individuals from and to cities in the US, finding that city to city migration follows scaling laws, so that the city size is a significant factor in determining whether, or not, an individual decides to migrate and the city size of both the origin and destination play key roles in the selection of the destination. We observe that individuals from small cities tend to migrate more frequently, tending to move to similar-sized cities, whereas individuals from large cities do not migrate so often, but when they do, they tend to move to other large cities. Building upon these findings we develop a scaling model which describes internal migration as a two-step decision process, demonstrating that it can partially explain migration fluxes based solely on city size. We then consider the impact of distance and construct a gravity-scaling model by combining the observed scaling patterns with the gravity law of migration. Results show that the scaling laws are a significant feature of human migration and that the inclusion of scaling can overcome the limits of the gravity and the radiation models of human migration.Source: PLOS ONE, vol. 13 (issue 7), pp. 1-19
DOI: 10.1371/journal.pone.0199892
Project(s): CIMPLEX
, SoBigData Metrics:
See at:
PLoS ONE | CNR IRIS | PLoS ONE | ISTI Repository | CNR IRIS
2020
Conference article
Open Access
Digital footprints of international migration on twitter
Kim J, Sirbu A, Giannotti F, Gabrielli L
Studying migration using traditional data has some limitations. To date, there have been several studies proposing innovative methodologies to measure migration stocks and flows from social big data. Nevertheless, a uniform definition of a migrant is difficult to find as it varies from one work to another depending on the purpose of the study and nature of the dataset used. In this work, a generic methodology is developed to identify migrants within the Twitter population. This describes a migrant as a person who has the current residence different from the nationality. The residence is defined as the location where a user spends most of his/her time in a certain year. The nationality is inferred from linguistic and social connections to a migrant's country of origin. This methodology is validated first with an internal gold standard dataset and second with two official statistics, and shows strong performance scores and correlation coefficients. Our method has the advantage that it can identify both immigrants and emigrants, regardless of the origin/destination countries. The new methodology can be used to study various aspects of migration, including opinions, integration, attachment, stocks and flows, motivations for migration, etc. Here, we exemplify how trending topics across and throughout different migrant communities can be observed.DOI: 10.1007/978-3-030-44584-3_22
Project(s): HumMingBird, SoBigData
Metrics:
Kim J, Sirbu A, Giannotti F, Gabrielli L
Studying migration using traditional data has some limitations. To date, there have been several studies proposing innovative methodologies to measure migration stocks and flows from social big data. Nevertheless, a uniform definition of a migrant is difficult to find as it varies from one work to another depending on the purpose of the study and nature of the dataset used. In this work, a generic methodology is developed to identify migrants within the Twitter population. This describes a migrant as a person who has the current residence different from the nationality. The residence is defined as the location where a user spends most of his/her time in a certain year. The nationality is inferred from linguistic and social connections to a migrant's country of origin. This methodology is validated first with an internal gold standard dataset and second with two official statistics, and shows strong performance scores and correlation coefficients. Our method has the advantage that it can identify both immigrants and emigrants, regardless of the origin/destination countries. The new methodology can be used to study various aspects of migration, including opinions, integration, attachment, stocks and flows, motivations for migration, etc. Here, we exemplify how trending topics across and throughout different migrant communities can be observed.DOI: 10.1007/978-3-030-44584-3_22
Project(s): HumMingBird
, SoBigData Metrics:
See at:
Lecture Notes in Computer Science | CNR IRIS | link.springer.com | link.springer.com | ISTI Repository | CNR IRIS
2021
Other
Open Access
Predicting vehicles parking behaviour in shared premises for aggregated EV electricity demand response programs
Monteiro De Lira V, Pallonetto F, Gabrielli L, Renso C
The global electric car sales in 2020 continued to exceed the expectations climbing to over 3 millions and reaching a market share of over 4%. However, uncertainty of generation caused by higher penetration of renewable energies and the advent of Electrical Vehicles (EV) with their additional electricity demand could cause strains to the power system, both at distribution and transmission levels. Demand response aggregation and load control will enable greater grid stability and greater penetration of renewable energies into the grid. The present work fits this context in supporting charging optimization for EV in parking premises assuming a incumbent high penetration of EVs in the system. We propose a methodology to predict an estimation of the parking duration in shared parking premises with the objective of estimating the energy requirement of a specific parking lot, evaluate optimal EVs charging schedule and integrate the scheduling into a smart controller. We formalize the prediction problem as a supervised machine learning task to predict the duration of the parking event before the car leaves the slot. This predicted duration feeds the energy management system that will allocate the power over the duration reducing the overall peak electricity demand. We structure our experiments inspired by two research questions aiming to discover the accuracy of the proposed machine learning approach and the most relevant features for the prediction models. We experiment different algorithms and features combination for 4 datasets from 2 different campus facilities in Italy and Brazil. Using both contextual and time of the day features, the overall results of the models shows an higher accuracy compared to a statistical analysis based on frequency, indicating a viable route for the development of accurate predictors for sharing parking premises energy management systems
Monteiro De Lira V, Pallonetto F, Gabrielli L, Renso C
The global electric car sales in 2020 continued to exceed the expectations climbing to over 3 millions and reaching a market share of over 4%. However, uncertainty of generation caused by higher penetration of renewable energies and the advent of Electrical Vehicles (EV) with their additional electricity demand could cause strains to the power system, both at distribution and transmission levels. Demand response aggregation and load control will enable greater grid stability and greater penetration of renewable energies into the grid. The present work fits this context in supporting charging optimization for EV in parking premises assuming a incumbent high penetration of EVs in the system. We propose a methodology to predict an estimation of the parking duration in shared parking premises with the objective of estimating the energy requirement of a specific parking lot, evaluate optimal EVs charging schedule and integrate the scheduling into a smart controller. We formalize the prediction problem as a supervised machine learning task to predict the duration of the parking event before the car leaves the slot. This predicted duration feeds the energy management system that will allocate the power over the duration reducing the overall peak electricity demand. We structure our experiments inspired by two research questions aiming to discover the accuracy of the proposed machine learning approach and the most relevant features for the prediction models. We experiment different algorithms and features combination for 4 datasets from 2 different campus facilities in Italy and Brazil. Using both contextual and time of the day features, the overall results of the models shows an higher accuracy compared to a statistical analysis based on frequency, indicating a viable route for the development of accurate predictors for sharing parking premises energy management systems
See at:
arxiv.org | CNR IRIS | ISTI Repository | CNR IRIS
2022
Conference article
Open Access
Predicting vehicles parking behaviour for EV recharge optimization
Monteiro De Lira V, Pallonetto F, Gabrielli L, Renso C
The global electric car sales in 2020 continued to exceed the expectations climbing to over 3 millions and reaching a market share of over 4%. However, uncertainty of generation caused by higher penetration of renewable energies and the advent of Electrical Vehicles (EV) with their additional electricity demand could cause strains to the power system, both at distribution and transmission levels. The present work fits this context in supporting charging optimization for EV in parking premises assuming a incumbent high penetration of EVs in the system. We propose a methodology to predict an estimation of the parking duration in shared parking premises with the objective of estimating the energy requirement of a specific parking lot, evaluate optimal EVs charging schedule and integrate the scheduling into a smart controller. We formalize the prediction problem as a supervised machine learning task to predict the duration of the parking event before the car leaves the slot. This predicted duration feeds the energy management system that will allocate the power over the duration reducing the overall peak electricity demand. We experiment different algorithms and features combination for 4 datasets from 2 different campus facilities in Italy and Brazil. Using both contextual and time of the day features, the overall results of the models shows an higher accuracy compared to a statistical analysis based on frequency, indicating a viable route for the development of accurate predictors for sharing parking premises energy management systems.Source: CEUR WORKSHOP PROCEEDINGS, pp. 199-206. Tirrenia, Pisa, Italy, 19-22/06/2022
Monteiro De Lira V, Pallonetto F, Gabrielli L, Renso C
The global electric car sales in 2020 continued to exceed the expectations climbing to over 3 millions and reaching a market share of over 4%. However, uncertainty of generation caused by higher penetration of renewable energies and the advent of Electrical Vehicles (EV) with their additional electricity demand could cause strains to the power system, both at distribution and transmission levels. The present work fits this context in supporting charging optimization for EV in parking premises assuming a incumbent high penetration of EVs in the system. We propose a methodology to predict an estimation of the parking duration in shared parking premises with the objective of estimating the energy requirement of a specific parking lot, evaluate optimal EVs charging schedule and integrate the scheduling into a smart controller. We formalize the prediction problem as a supervised machine learning task to predict the duration of the parking event before the car leaves the slot. This predicted duration feeds the energy management system that will allocate the power over the duration reducing the overall peak electricity demand. We experiment different algorithms and features combination for 4 datasets from 2 different campus facilities in Italy and Brazil. Using both contextual and time of the day features, the overall results of the models shows an higher accuracy compared to a statistical analysis based on frequency, indicating a viable route for the development of accurate predictors for sharing parking premises energy management systems.Source: CEUR WORKSHOP PROCEEDINGS, pp. 199-206. Tirrenia, Pisa, Italy, 19-22/06/2022
See at:
ceur-ws.org | CNR IRIS | ISTI Repository | CNR IRIS
2023
Conference article
Open Access
Predicting EV parking behaviour in shared premises
Monteiro De Lira V., Pallonetto F., Gabrielli L., Renso C.
The global electric car sales continued to exceed the expectations climbing to over 3 millions and reaching a market share of over 4%. However, uncertainty of generation caused by higher penetration of renewable energies and the advent of Electrical Vehicles (EV) with their additional electricity demand could cause strains to the power system, both at distribution and transmission levels. The present work fits this context in supporting charging optimization for EV in parking premises assuming a incumbent high penetration of EVs in the system. We propose a methodology to predict an estimation of the parking duration in shared parking premises. The final objective is estimating the energy requirement of a specific parking lot, evaluate optimal EVs charging schedule and integrate the scheduling into a smart controller. We formalize the prediction problem as a supervised machine learning task to predict the duration of the parking event before the car leaves the slot. We test the proposed approach in a combination of datasets from 2 different campus facilities in Italy and Brazil. The overall results of the models shows an higher accuracy compared to a statistical analysis based on frequency, indicating a viable route for the development of accurate predictors for sharing parking premises energy management systems.Source: BMDA 2023 - 5th International Workshop on Big Mobility Data Analytics co-located with EDBT/ICDT 2023 Joint Conference, Ioannina, Greece, 28/03/2023
Project(s): ERANet SmartGridPlus
Monteiro De Lira V., Pallonetto F., Gabrielli L., Renso C.
The global electric car sales continued to exceed the expectations climbing to over 3 millions and reaching a market share of over 4%. However, uncertainty of generation caused by higher penetration of renewable energies and the advent of Electrical Vehicles (EV) with their additional electricity demand could cause strains to the power system, both at distribution and transmission levels. The present work fits this context in supporting charging optimization for EV in parking premises assuming a incumbent high penetration of EVs in the system. We propose a methodology to predict an estimation of the parking duration in shared parking premises. The final objective is estimating the energy requirement of a specific parking lot, evaluate optimal EVs charging schedule and integrate the scheduling into a smart controller. We formalize the prediction problem as a supervised machine learning task to predict the duration of the parking event before the car leaves the slot. We test the proposed approach in a combination of datasets from 2 different campus facilities in Italy and Brazil. The overall results of the models shows an higher accuracy compared to a statistical analysis based on frequency, indicating a viable route for the development of accurate predictors for sharing parking premises energy management systems.Source: BMDA 2023 - 5th International Workshop on Big Mobility Data Analytics co-located with EDBT/ICDT 2023 Joint Conference, Ioannina, Greece, 28/03/2023
Project(s): ERANet SmartGridPlus
See at:
ceur-ws.org | ISTI Repository | CNR ExploRA
2012
Conference article
Open Access
Identifying users profiles from mobile calls habits
Furletti B, Gabrielli L, Rinzivillo S, Renso C
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.DOI: 10.1145/2346496.2346500
Project(s): DATA SIM
Metrics:
Furletti B, Gabrielli L, Rinzivillo S, Renso C
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.DOI: 10.1145/2346496.2346500
Project(s): DATA SIM
Metrics:
See at:
www.cs.uic.edu | doi.org | CNR IRIS | CNR IRIS
2013
Conference article
Restricted
Pisa tourism fluxes observatory: deriving mobility indicators from GSM calls habits
Furletti B, Gabrielli L, Rinzivillo S, Renso C
The necessity to improve the management of the resources, urged many local governments to adhere to European initiatives in the context of competitiveness and sustainability, for creating the right balance between the welfare of tourists, the needs of the natural and cultural environment and the development and competitiveness of destinations and businesses. For many Italian Municipalities, this requirements become concrete with the establishment of a tourism monitoring systems that aims at survey these phenomenon through the analysis of heterogeneous data ranging from information of the territory, energy consumption, use of the land, and linked data (arrival and departure from the airport, bus, hotels etc). We describe the permanent observatory of touristic fluxes we realized in the town of Pisa where the standard indicators have been extended with an indicator of people presence extracted from mobile GSM call data and other exploratory analyses made by using the mobile phone data.we developed a method to partition the users into residents, commuters, in transit and visitors starting from a spatio-temporal profile inferred from people call habits.
Furletti B, Gabrielli L, Rinzivillo S, Renso C
The necessity to improve the management of the resources, urged many local governments to adhere to European initiatives in the context of competitiveness and sustainability, for creating the right balance between the welfare of tourists, the needs of the natural and cultural environment and the development and competitiveness of destinations and businesses. For many Italian Municipalities, this requirements become concrete with the establishment of a tourism monitoring systems that aims at survey these phenomenon through the analysis of heterogeneous data ranging from information of the territory, energy consumption, use of the land, and linked data (arrival and departure from the airport, bus, hotels etc). We describe the permanent observatory of touristic fluxes we realized in the town of Pisa where the standard indicators have been extended with an indicator of people presence extracted from mobile GSM call data and other exploratory analyses made by using the mobile phone data.we developed a method to partition the users into residents, commuters, in transit and visitors starting from a spatio-temporal profile inferred from people call habits.
See at:
CNR IRIS | CNR IRIS | perso.uclouvain.be
2013
Conference article
Restricted
Where have you been today? Annotating trajectories with DayTag
Rinzivillo S, De Lucca Siqueira F, Gabrielli L, Renso C
Traditionally, the information about human mobility behav- ior, called diary, is acquired from volunteers by means of paper-and- pencil surveys. These diaries, representing the mobile activities of indi- viduals, are semantically rich, but lack in spatial and temporal precision. An alternative way is collecting diaries by annotating with activities the GPS tracks of individuals. This is more accurate from a spatio-temporal point of view, but the manual annotation becomes a burdensome work for the user. The tool we propose, called DayTag, is designed as a per- sonal assistant to help an individual to reconstruct her/his diary from the GPS tracks collected by a smartphone. The user interacts through the software to visualize and annotate the trajectories, thus resulting in a simple way to get user diaries.Project(s): SEEK
Rinzivillo S, De Lucca Siqueira F, Gabrielli L, Renso C
Traditionally, the information about human mobility behav- ior, called diary, is acquired from volunteers by means of paper-and- pencil surveys. These diaries, representing the mobile activities of indi- viduals, are semantically rich, but lack in spatial and temporal precision. An alternative way is collecting diaries by annotating with activities the GPS tracks of individuals. This is more accurate from a spatio-temporal point of view, but the manual annotation becomes a burdensome work for the user. The tool we propose, called DayTag, is designed as a per- sonal assistant to help an individual to reconstruct her/his diary from the GPS tracks collected by a smartphone. The user interacts through the software to visualize and annotate the trajectories, thus resulting in a simple way to get user diaries.Project(s): SEEK
2014
Contribution to book
Restricted
Transportation planning based on GSM traces: a case study on Ivory Coast
Nanni M, Trasarti R, Furletti B, Gabrielli L, Van Der Mede P, De Brujin J, De Romph E, Bruil G
In this work we present an analysis process that exploits mobile phone transaction (trajectory) data to infer a transport demand model for the territory under monitoring. In particular, long-term analysis of individual call traces are performed to reconstruct systematic movements, and to infer an origin-destination matrix. We will show a case study on Ivory Coast, with emphasis on its major urbanization Abidjan. The case study includes the exploitation of the inferred mobility demand model in the construction of a transport model that projects the demand onto the transportation network (obtained from open data), and thus allows an understanding of current and future infrastructure requirements of the country.DOI: 10.1007/978-3-319-04178-0_2
Metrics:
Nanni M, Trasarti R, Furletti B, Gabrielli L, Van Der Mede P, De Brujin J, De Romph E, Bruil G
In this work we present an analysis process that exploits mobile phone transaction (trajectory) data to infer a transport demand model for the territory under monitoring. In particular, long-term analysis of individual call traces are performed to reconstruct systematic movements, and to infer an origin-destination matrix. We will show a case study on Ivory Coast, with emphasis on its major urbanization Abidjan. The case study includes the exploitation of the inferred mobility demand model in the construction of a transport model that projects the demand onto the transportation network (obtained from open data), and thus allows an understanding of current and future infrastructure requirements of the country.DOI: 10.1007/978-3-319-04178-0_2
Metrics:
See at:
doi.org | CNR IRIS | CNR IRIS | link.springer.com
2013
Conference article
Restricted
Analysis of GSM calls data for understanding user mobility behavior
Furletti B, Gabrielli L, Renso C, Rinzivillo S
This information about our GSM calls is stored by the TelCo operator in large volumes and with strict privacy constraints making it challenging the analysis of these fingerprints for inferring mobility behavior. This paper proposes a strategy for mobility behavior identification based on aggregated calling profiles of mobile phone users. This compact representation of the user call profiles is the input of the mining algorithm for automatically classifying various kinds of mobility behavior. A further advantage of having defined the call profiles is that the analysis phase is based on summarized privacy-preserving representation of the original data. We show how these call profiles permit to design a two step process - implemented into a system - based on a bootstrap phase and a running phase for classifying users into behavior categories. We evaluated the system in two case studies where individuals are classified into residents, commuters and visitors. We conclude the paper with a discussion which emphasizes the role of the call profiles for the design of a new collaboration model between data provider and data analyst.DOI: 10.1109/bigdata.2013.6691621
Project(s): DATA SIM
Metrics:
Furletti B, Gabrielli L, Renso C, Rinzivillo S
This information about our GSM calls is stored by the TelCo operator in large volumes and with strict privacy constraints making it challenging the analysis of these fingerprints for inferring mobility behavior. This paper proposes a strategy for mobility behavior identification based on aggregated calling profiles of mobile phone users. This compact representation of the user call profiles is the input of the mining algorithm for automatically classifying various kinds of mobility behavior. A further advantage of having defined the call profiles is that the analysis phase is based on summarized privacy-preserving representation of the original data. We show how these call profiles permit to design a two step process - implemented into a system - based on a bootstrap phase and a running phase for classifying users into behavior categories. We evaluated the system in two case studies where individuals are classified into residents, commuters and visitors. We conclude the paper with a discussion which emphasizes the role of the call profiles for the design of a new collaboration model between data provider and data analyst.DOI: 10.1109/bigdata.2013.6691621
Project(s): DATA SIM
Metrics:
See at:
doi.org | CNR IRIS | ieeexplore.ieee.org | CNR IRIS
2013
Conference article
Restricted
MP4A project: mobility planning for Africa
Nanni M, Trasarti R, Furletti B, Gabrielli L, Van Der Mede P, De Bruijn J, De Romph E, Bruil G
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.
Nanni M, Trasarti R, Furletti B, Gabrielli L, Van Der Mede P, De Bruijn J, De Romph E, Bruil G
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.
See at:
CNR IRIS | CNR IRIS | perso.uclouvain.be
2015
Other
Restricted
Application of ETL techniques for SmartCity Malaga dataset
Rinzivillo S, Pennacchioli D, Gabrielli L, Giannotti F
In this document we present a framework to aggregate data collected by sensors deployed in a portion of a distribution grid. The system provides functionalities to model the topological properties of the distribution grid, to harmonize and integrate readings coming from the sensors, to store and query efficiently the data, to visualize with a clear interface the timeseries collected. The rest of the document is organized as follows: first we show how we model the distribution grid with a graph-based representation; we describe the extraction, transformation and loading procedure; then we describe the visual interface to present the data to the analyst.
Rinzivillo S, Pennacchioli D, Gabrielli L, Giannotti F
In this document we present a framework to aggregate data collected by sensors deployed in a portion of a distribution grid. The system provides functionalities to model the topological properties of the distribution grid, to harmonize and integrate readings coming from the sensors, to store and query efficiently the data, to visualize with a clear interface the timeseries collected. The rest of the document is organized as follows: first we show how we model the distribution grid with a graph-based representation; we describe the extraction, transformation and loading procedure; then we describe the visual interface to present the data to the analyst.
2015
Other
Restricted
Compatibility analysis of the current mobility with electrified vehicles (D4)
Rinzivillo S, Giannotti F, Pennacchioli D, Gabrielli L
The availability of GPS-enabled devices has fostered the collection of large datasets of movements of people. This provides us a big opportunity to study human mobility behavior and to understand the key features to modify in order to improve the efficiency of individual movements. This efficiency has been studied in terms of mitigation of side effects of high density traffic, like jams, pollution, space occupancy. In this work, we concentrate on the study of the energy efficiency of movements, by considering a new emerging mean of transportation based on electric powered engines. In this document we explore the compatibility of the current mobility habits with electric engine technology, discussing improvement and solution to promote or improve the spatial range and extent of current vehicles.
Rinzivillo S, Giannotti F, Pennacchioli D, Gabrielli L
The availability of GPS-enabled devices has fostered the collection of large datasets of movements of people. This provides us a big opportunity to study human mobility behavior and to understand the key features to modify in order to improve the efficiency of individual movements. This efficiency has been studied in terms of mitigation of side effects of high density traffic, like jams, pollution, space occupancy. In this work, we concentrate on the study of the energy efficiency of movements, by considering a new emerging mean of transportation based on electric powered engines. In this document we explore the compatibility of the current mobility habits with electric engine technology, discussing improvement and solution to promote or improve the spatial range and extent of current vehicles.
2015
Conference article
Open Access
Detecting and understanding big events in big cities
Furletti B, Trasarti R, Gabrielli L, Smoreda Z, Vanhoof M, Ziemlicki C
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 Fete de la Musique using a privacy preserving protocol.
Furletti B, Trasarti R, Gabrielli L, Smoreda Z, Vanhoof M, Ziemlicki C
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 Fete de la Musique using a privacy preserving protocol.
See at:
CNR IRIS | www.netmob.org | CNR IRIS