See at: CNR IRIS | CNR IRIS

2018 Journal article Open Access

Data-driven generation of spatio-temporal routines in human mobility
Pappalardo L, Simini F
The generation of realistic spatio-temporal trajectories of human mobility is of fundamental importance in a wide range of applications, such as the developing of protocols for mobile ad-hoc networks or what-if analysis in urban ecosystems. Current generative algorithms fail in accurately reproducing the individuals' recurrent schedules and at the same time in accounting for the possibility that individuals may break the routine during periods of variable duration. In this article we present Ditras (DIary-based TRAjectory Simulator), a framework to simulate the spatio-temporal patterns of human mobility. Ditras operates in two steps: the generation of a mobility diary and the translation of the mobility diary into a mobility trajectory. We propose a data-driven algorithm which constructs a diary generator from real data, capturing the tendency of individuals to follow or break their routine. We also propose a trajectory generator based on the concept of preferential exploration and preferential return. We instantiate Ditras with the proposed diary and trajectory generators and compare the resulting algorithm with real data and synthetic data produced by other generative algorithms, built by instantiating Ditras with several combinations of diary and trajectory generators. We show that the proposed algorithm reproduces the statistical properties of real trajectories in the most accurate way, making a step forward the understanding of the origin of the spatio-temporal patterns of human mobility.Source: DATA MINING AND KNOWLEDGE DISCOVERY, vol. 32 (issue 3), pp. 787-829
DOI: 10.1007/s10618-017-0548-4
DOI: 10.48550/arxiv.1607.05952
Project(s): CIMPLEX , Dynamic equation approach to forecast long-range demographic scenarios , SoBigData
Metrics:

See at: arXiv.org e-Print Archive | Data Mining and Knowledge Discovery | Data Mining and Knowledge Discovery | CNR IRIS | link.springer.com | Data Mining and Knowledge Discovery | ISTI Repository | Explore Bristol Research | doi.org | CNR IRIS

2018 Conference article Open Access

Weak nodes detection in urban transport systems: planning for resilience in Singapore
Ferretti M, Barlacchi G, Pappalardo L, Lucchini L, Lepri B
The availability of massive data-sets describing human mobility offers the possibility to design simulation tools to monitor and improve the resilience of transport systems in response to traumatic events such as natural and man-made disasters (e.g., floods, terrorist attacks, etc...). In this perspective we propose ACHILLES, an application to models people's movements in a given transport mode through a multiplex network representation based on mobility data. ACHILLES is a web-based application which provides an easy-to-use interface to explore the mobility fluxes and the connectivity of every urban zone in a city, as well as to visualize changes in the transport system resulting from the addition or removal of transport modes, urban zones and single stops. Notably, our application allows the user to assess the overall resilience of the transport network by identifying its weakest node, i.e. Urban Achilles Heel, with reference to the ancient Greek mythology. To demonstrate the impact of ACHILLES for humanitarian aid we consider its application to a real-world scenario by exploring human mobility in Singapore in response to flood prevention.DOI: 10.1109/dsaa.2018.00061
DOI: 10.48550/arxiv.1809.07839
Project(s): SoBigData
Metrics:

See at: arXiv.org e-Print Archive | arxiv.org | CNR IRIS | ieeexplore.ieee.org | ISTI Repository | doi.org | doi.org | CNR IRIS | CNR IRIS

2019 Conference article Open Access

Human mobility from theory to practice: data, models and applications
Simini F, Pellungrini R, Barlacchi G, Pappalardo L
The inclusion of tracking technologies in personal devices opened the doors to the analysis of large sets of mobility data like GPS traces and call detail records. This tutorial presents an overview of both modeling principles of human mobility and machine learning models applicable to specific problems. We review the state of the art of five main aspects in human mobility: (1) human mobility data landscape; (2) key measures of individual and collective mobility; (3) generative models at the level of individual, population and mixture of the two; (4) next location prediction algorithms; (5) applications for social good. For each aspect, we show experiments and simulations using the Python library "scikit-mobility" developed by the presenters of the tutorial.DOI: 10.1145/3308560.3320099
Project(s): SoBigData
Metrics:

See at: arpi.unipi.it | Explore Bristol Research | dl.acm.org | doi.org | CNR IRIS | CNR IRIS

2019 Journal article Open Access

Relationship between external and internal workloads in elite soccer players: Comparison between rate of perceived exertion and training load
Rossi A, Perri E, Pappalardo L, Cintia P, Iaia Fm
The use of machine learning (ML) in soccer allows for the management of a large amount of data deriving from the monitoring of sessions and matches. Although the rate of perceived exertion (RPE), training load (S-RPE), and global position system (GPS) are standard methodologies used in team sports to assess the internal and external workload; how the external workload affects RPE and S-RPE remains still unclear. This study explores the relationship between both RPE and SRPE and the training workload through ML. Data were recorded from 22 elite soccer players, in 160 training sessions and 35 matches during the 2015/2016 season, by using GPS tracking technology. A feature selection process was applied to understand which workload features influence RPE and SRPE the most. Our results show that the training workloads performed in the previous week have a strong effect on perceived exertion and training load. On the other hand, the analysis of our predictions shows higher accuracy for medium RPE and S-RPE values compared with the extremes. These results provide further evidence of the usefulness of ML as a support to athletic trainers and coaches in understanding the relationship between training load and individual-response in team sports.Source: APPLIED SCIENCES, vol. 9 (issue 23)
DOI: 10.3390/app9235174
Project(s): SoBigData
Metrics:

See at: Applied Sciences | CNR IRIS | ISTI Repository | www.mdpi.com | Applied Sciences | CNR IRIS

2019 Other Open Access

scikit-mobility: a Python library for the analysis, generation and risk assessment of mobility data
Pappalardo L, Simini F, Barlacchi G, Pellungrini R
The last decade has witnessed the emergence of massive mobility data sets, such as tracks generated by GPS devices, call detail records, and geo-tagged posts from social media platforms. These data sets have fostered a vast scientific production on various applications of human mobility analysis, ranging from computational epidemiology to urban planning and transportation engineering. A strand of literature addresses data cleaning issues related to raw spatiotemporal trajectories, while the second line of research focuses on discovering the statistical "laws" that govern human movements. A significant effort has also been put on designing algorithms to generate synthetic trajectories able to reproduce, realistically, the laws of human mobility. Last but not least, a line of research addresses the crucial problem of privacy, proposing techniques to perform the re-identification of individuals in a database. Despite the increasing importance of human mobility analysis for many scientific and industrial domains, a view on state of the art cannot avoid noticing that there is no statistical software that can support scientists and practitioners with all the aspects mentioned above of mobility data analysis. To fill this gap, we propose scikit-mobility, a Python library that has the ambition of providing an environment to reproduce existing research, analyze mobility data, and simulate human mobility habits. scikit-mobility is efficient and easy to use as it extends the well-known standard pandas, a popular Python library for data analysis. Moreover, scikit-mobility provides the user with many functionalities, from visualizing trajectories to generating synthetic data, from analyzing the statistical patterns of trajectories to assessing the privacy risk related to the analysis of mobility data sets.Project(s): SoBigData

See at: arxiv.org | CNR IRIS | ISTI Repository | CNR IRIS

scikit-mobility
Pappalardo L, Simini F, Barlacchi G, Pellungrini R
scikit-mobility is a library for human mobility analysis in Python. The library allows to: - represent trajectories and mobility flows with proper data structures, TrajDataFrame and FlowDataFrame. - manage and manipulate mobility data of various formats (call detail records, GPS data, data from social media, survey data, etc.); - extract mobility metrics and patterns from data, both at individual and collective level (e.g., length of displacements, characteristic distance, origin-destination matrix, etc.) - generate synthetic individual trajectories using standard mathematical models (random walk models, exploration and preferential return model, etc.) - generate synthetic mobility flows using standard migration models (gravity model, radiation model, etc.) - assess the privacy risk associated with a mobility data setProject(s): SoBigData

See at: github.com | CNR IRIS

Exploring spatio-temporal soccer events using public event data
Pappalardo L, Rossi A, Cintia P
Software for the exploration of an open collection of soccer-logs described in the following paper: (PCR2019) Pappalardo, L., Cintia, P., Rossi, A. et al. A public data set of spatio-temporal match events in soccer competitions. Nature Scientific Data 6, 236 (2019). https://doi.org/10.1038/s41597-019-0247-7Project(s): SoBigData

See at: github.com | CNR IRIS

Soccer match event dataset
Pappalardo L, Massucco E
Soccer analytics is attracting an increasing interest of academia and industry, thanks to the availability of sensing technologies that provide high-fidelity data streams extracted from every match. Unfortunately, these detailed data are owned by specialized companies and hence are rarely publicly available for scientific research. To fill this gap, we provide to the public the largest open collection of soccer-logs ever released, collected by Wyscout (https://wyscout.com/) containing all the spatio-temporal events (passes, shots, fouls, etc.) that occur during all matches of an entire season of seven competitions (La Liga, Serie A, Bundesliga, Premier League, Ligue 1, FIFA World Cup 2018, UEFA Euro Cup 2016). A match event contains information about its position, time, outcome, player and characteristics. This dataset has been used recently during the Soccer Data Challenge (https://sobigdata-soccerchallenge.it/) and, to the best of our knowledge, it is the largest public collection of soccer-logs.Project(s): SoBigData

See at: figshare.com | CNR IRIS

See at: github.com | CNR IRIS

Human mobility analysis and simulation with Python
Pappalardo L, Simini F, Barlacchi G, Pellungrini R
The availability of geo-spatial mobility data (e.g., GPS traces, call detail and social media records) is a trend that will grow in the near future. For this reason, understanding human mobility is of paramount importance for many present and future applications, such as traffic forecasting, urban planning, and epidemic modeling, and hence for many actors, from urban planners to decision-makers and advertising companies. In this hands-on tutorial at the Applied Machine Learning Days 2020 (AMLD2020) we present, with a strong focus on code implementation, an overview of the fundamental principles underlying the analysis of big mobility data. Starting from mobility data describing the whereabouts of individuals on a territory for a large-enough observation window, we drive the audience through the extraction of mobility patterns and measures by using scikit-mobility, a specific Python library designed by the tutorial presenters. The library allows the user to: filter and clean raw mobility data by using standard techniques proposed in the mobility data mining literature; analyze mobility data by using the main measures characterizing human mobility patterns (e.g., radius of gyration, daily motifs, mobility entropy); simulate individual and collective mobility by executing the most common human mobility models (e.g., gravity and radiation models, exploration and preferential return model); assess the privacy risk related to the analysis of a real-world mobility data set. Since it is supposed to be a practical hands-on tutorial, for every concept presented during the training we show a practical code example presented through the Jupyter notebook. scikit-mobility is a starting point for the development of urban simulation and what-if analysis, e.g., simulating changes in urban mobility after the construction of a new infrastructure or when traumatic events occur like epidemic diffusion, terrorist attacks or international events.Project(s): SoBigData

See at: github.com | CNR IRIS

2020 Other Open Access

Analysis of technical attributes of male and female national football teams: a comparison through a statistical machine learning approach
Pontillo G., Pappalardo L.
Too often women's football has been compared to men's football mainly on the basis of the players' physical attributes, offering an incomplete analysis of when the characteristics of any football team are studied analytically. Thanks to the availability of an open soccer-logs data set provided by Wyscout, this thesis aims to statistically analyse and compare male and female national football teams based on their technical qualities, measured through the event data obtained from the last World Cup championships. An event could be defined as a certain action, such as a pass, a shot, a foul, a save attempt, and so on, made by a team's player in a match. First results show, for example, that there are significant differences in the number of key playing events, such as passes, percentage of accurate passes and free kicks made by the national teams during a match. Through the use of particular methods and algorithms, there were computed variables related to the technical characteristics of a team, such as the average time between two passes and the average ball possession recovery time, which can also define the intensity of a game, and variables that summarize and quantify the individual and collective performance of a team's players within a single value, such as the H indicator or the players' ratings aggregated for each team via mean and standard deviation. For example, the more the ratings' standard deviation, the more, in a particular match, the team was characterized by players that, individually, outperformed respect to their teammates. Finally, all these features were used into advanced classification algorithms such as Decision Tree, Random Forest and AdaBoost with the task of classifying a team in a game as male (class 0 ) or female (class 1 ). All the classifiers were validated through a 10-fold Cross Validation on a training set and they all showed a good predictive performance, indicating that it is possible to distinct a male football team from a female one (and vice versa) on technical skills. Moreover, after fitting a Decision Tree on different versions of training set and looking at the importance that each variable had in the decision path every time, we find that the most important differences underlie in variables such as players' individual performance variability, pass velocity, ball recovery time and the percentage of accurate passes made by the teams.Project(s): SoBigData

See at: drive.google.com | CNR IRIS | ISTI Repository | CNR IRIS

2017 Other Open Access

Predicting and explaining the popularity of songs with data mining
Campagna M., Pappalardo L.
Data mining techniques recently were used to solve several problems related to music. This dissertation studies songs popularity in order to find out factors that make a song popular or not. The outcomes obtained are also used to give an answer to the myth of four chords. This myth in fact asserts that all popular songs can be played by using only four chords. The entire project covers all the stages of Knowledge Discovery in the Databasesprocess. We aimed to make a first research on songs popularity. In particular, data on music songs are collected and studied. These data are also used to create several models using data mining techniques. The problem of predicting and explaining songs popularity is studied by using both regression and classification algorithms. Finally, the fittest model is interpreted and tested with specific instances in order to achieve the goal.Project(s): SoBigData

See at: etd.adm.unipi.it | CNR IRIS | ISTI Repository | CNR IRIS

2017 Other Open Access

Transfer Network Analysis: evoluzione del calciomercato dal dopoguerra ai giorni nostri
Mastini S., Pappalardo L.
La Tesi si pone come obiettivo lo studio delle reti e delle basi di dati collegate al mondo dello sport, in particolare quello del calcio. L'analisi dei flussi di mercato del calcio, condotta seguendo la dottrina della data analytics, permette di capire come si sia evoluto il calciomercato nell'arco temporale che va dal 1950 al 2014. A partire dallo studio delle reti, portando a termine misure statistiche con granularità annua, è possibile estrapolare dati sull'internazionalizzazione del sistema mondiale e i momenti che ne hanno sancito i cambiamenti epocali. Questo tipo di approfondimento ci permette di monitorare anche lo stato dell'arte dei cinque maggiori campionati d'Europa (Serie A, Premier League, Liga, Ligue 1 e Bundesliga), ricostruendone così anche l'interconnessione tra i club che ne fanno parte. Dopo aver vagliato la situazione complessiva, ci si è poi focalizzati sulla ricostruzione delle linee temporali del calciomercato europeo, analizzando in primo luogo il tipo di trasferimento registrato e la sua incidenza nel tempo nonché la sua valenza sociale. Successivamente, cercando di scoprire gli escamotage e i bilanci finanziari che permettono ai club dei maggiori campionati europei di giustificare il proprio bilancio a fronte anche dei risultati sportivi ottenuti. L'indagine conseguita in tal senso, ha preso come punto di riferimento soprattutto la Serie A e la Premier League per ragioni di prestigio storico e non solo, anche per l'importanza avuta nel sancire il corso dell'evoluzione del calcio mondiale.Project(s): SoBigData

See at: etd.adm.unipi.it | CNR IRIS | ISTI Repository | CNR IRIS

Assessing Privacy Risk & Quality of Spatio-temporal Data
Pellungrini R.
Mobility data are a fundamental source of information for studying human behavior and developing new services for users. In recent years, with the growing presence of smartphones in our lives and the increasing connectivity of devices used everyday, data regarding the whereabouts of individuals in time has become more and more available. However, the exchange and publication of such data may lead to dangerous privacy violations for the people involved. Malicious third parties may try and succeed in identifying individuals even in a deidentified dataset, by attacking in various ways the published data. In this work, we propose a study of the safeness of a common data framework for trajectories, in order to understand the levels of risk for the people involved. We will introduce and develop a simulation of a number of different types of attack and we will apply them to a real mobility dataset. We will then try to understand if such levels of risk can impair the safe use of the data themselves. We will also evaluate how the quality of the most used mobility measures changes by eliminating data of individuals with high privacy risk.Project(s): SoBigData

See at: etd.adm.unipi.it | CNR ExploRA

Analisi e profilazione dei comportamenti di videogiocatori online con tecniche di Data Mining
Grano C.
Il lavoro svolto verte sull'analisi dei comportamenti degli utenti-giocatori di un gioco mobile di un'azienda Spagnola (From The Bench SL). Le analisi sono state condotte con l'ausilio di Hadoop e Python grazie ai quali si è effettuata la profilazione degli utenti. L'obiettivo del lavoro è stato quello di studiare i comportamenti degli utenti per generare e migliorare le azioni di fidelizzazione.Project(s): SoBigData

See at: etd.adm.unipi.it | CNR ExploRA

PassNet
Sorano D, Cintia P, Pappalardo L
The code in this repository implements PassNet and ResBi, two models that perform pass annotation from soccer video broadcasts, and the Pass Tagging Interface, which allows a user to define the temporal window of the Pass event annotated by Wyscout. The code referes to the following paper: https://arxiv.org/abs/2007.06475Project(s): SoBigData

See at: github.com | CNR IRIS

Material for Soccer Data Cup
Pappalardo L, Cintia P
Materiale didattico per i partecipanti alla Soccer Data Cup, una competizione su dati calcistici per gli studenti delle scuole superiori.Project(s): SoBigData

See at: github.com | CNR IRIS

2020 Other Open Access

Deep Gravity: enhancing mobility flows generation with deep neural networks and geographic information
Simini F, Barlacchi G, Luca M, Pappalardo L
The movements of individuals within and among cities influence key aspects of our society, such as the objective and subjective well-being, the diffusion of innovations, the spreading of epidemics, and the quality of the environment. For this reason, there is increasing interest around the challenging problem of flow generation, which consists in generating the flows between a set of geographic locations, given the characteristics of the locations and without any information about the real flows. Existing solutions to flow generation are mainly based on mechanistic approaches, such as the gravity model and the radiation model, which suffer from underfitting and overdispersion, neglect important variables such as land use and the transportation network, and cannot describe non-linear relationships between these variables. In this paper, we propose the Multi-Feature Deep Gravity (MFDG) model as an effective solution to flow generation. On the one hand, the MFDG model exploits a large number of variables (e.g., characteristics of land use and the road network; transport, food, and health facilities) extracted from voluntary geographic information data (OpenStreetMap). On the other hand, our model exploits deep neural networks to describe complex non-linear relationships between those variables. Our experiments, conducted on commuting flows in England, show that the MFDG model achieves a significant increase in the performance (up to 250\% for highly populated areas) than mechanistic models that do not use deep neural networks, or that do not exploit geographic voluntary data. Our work presents a precise definition of the flow generation problem, which is a novel task for the deep learning community working with spatio-temporal data, and proposes a deep neural network model that significantly outperforms current state-of-the-art statistical models.Project(s): SoBigData-PlusPlus

See at: arxiv.org | CNR IRIS | ISTI Repository | CNR IRIS

2020 Other Open Access

Deep Learning for Human Mobility: a Survey on Data and Models
Luca M, Barlacchi G, Lepri B, Pappalardo L
The study of human mobility is crucial due to its impact on several aspects of our society, such as disease spreading, urban planning, well-being, pollution, and more. The proliferation of digital mobility data, such as phone records, GPS traces, and social media posts, combined with the outstanding predictive power of artificial intelligence, triggered the application of deep learning to human mobility. In particular, the literature is focusing on three tasks: next-location prediction, i.e., predicting an individual's future locations; crowd flow prediction, i.e., forecasting flows on a geographic region; and trajectory generation, i.e., generating realistic individual trajectories. Existing surveys focus on single tasks, data sources, mechanistic or traditional machine learning approaches, while a comprehensive description of deep learning solutions is missing. This survey provides: (i) basic notions on mobility and deep learning; (ii) a review of data sources and public datasets; (iii) a description of deep learning models and (iv) a discussion about relevant open challenges. Our survey is a guide to the leading deep learning solutions to next-location prediction, crowd flow prediction, and trajectory generation. At the same time, it helps deep learning scientists and practitioners understand the fundamental concepts and the open challenges of the study of human mobility.Project(s): SoBigData-PlusPlus

See at: arxiv.org | CNR IRIS | ISTI Repository | CNR IRIS