A5059674609- Sports Performance and Training
- Sports Analytics and Performance
- Human Mobility and Location-Based Analysis
- Video Analysis and Summarization
- Sports injuries and prevention
- Data-Driven Disease Surveillance
- Data Management and Algorithms
- Traffic Prediction and Management Techniques
- Data Visualization and Analytics
- COVID-19 epidemiological studies
- Geographic Information Systems Studies
- Time Series Analysis and Forecasting
- Cardiovascular and exercise physiology
- Genetics and Physical Performance
- Complex Network Analysis Techniques
- Traffic and Road Safety
- Anomaly Detection Techniques and Applications
- Material Properties and Processing
- Advanced Neuroimaging Techniques and Applications
- Privacy-Preserving Technologies in Data
- Tensor decomposition and applications
- Big Data and Business Intelligence
- Physical Activity and Health
- COVID-19 Digital Contact Tracing
- Urban, Neighborhood, and Segregation Studies
University of Pisa
2013-2024
Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo"
2013-2019
National Research Council
2017-2018
Injuries have a great impact on professional soccer, due to their large influence team performance and the considerable costs of rehabilitation for players. Existing studies in literature provide just preliminary understanding which factors mostly affect injury risk, while an evaluation potential statistical models forecasting injuries is still missing. In this paper, we propose multi-dimensional approach soccer that based GPS measurements machine learning. By using tracking technology,...
Abstract Soccer analytics is attracting increasing interest in academia and industry, thanks to the availability of sensing technologies that provide high-fidelity data streams for every match. Unfortunately, these detailed are owned by specialized companies hence rarely publicly available scientific research. To fill this gap, paper describes largest open collection soccer-logs ever released, containing all spatio-temporal events (passes, shots, fouls, etc.) occured during each match an...
The problem of evaluating the performance soccer players is attracting interest many companies and scientific community, thanks to availability massive data capturing all events generated during a match (e.g., tackles, passes, shots, etc.). Unfortunately, there no consolidated widely accepted metric for measuring quality in its facets. In this article, we design implement PlayeRank, data-driven framework that offers principled multi-dimensional role-aware evaluation players. We build our by...
The collection of huge amount tracking data made possible by the widespread use GPS devices, enabled analysis such for several applications domains, ranging from traffic management to advertisement and social studies. However, raw positioning data, as it is detected lacks semantic information since this does not natively provide any additional contextual like places that people visited or activities performed. Traditionally, collected hand filled questionnaire where a limited number users...
Sports analytics in general, and football (soccer USA) particular, have evolved recent years an amazing way, thanks to automated or semi-automated sensing technologies that provide high-fidelity data streams extracted from every game. In this paper we propose a data-driven approach show there is large potential boost the understanding of team performance. From observational games extract set pass-based performance indicators summarize them H indicator. We observe strong correlation among...
The availability of massive data about sports activities offers nowadays the opportunity to quantify relation between performance and success. In this study, we analyze more than 6000 games 10 million events in six European leagues investigate soccer competitions. We discover that a team’s position competition’s final ranking is significantly related its typical performance, as described by set technical features extracted from data. Moreover, find that, while victory defeats can be...
Women's football is gaining supporters and practitioners worldwide, raising questions about what the differences are with men's football. While two sports often compared based on players' physical attributes, we analyze spatio-temporal events during matches in last World Cups to compare male female teams their technical performance. We train an artificial intelligence model recognize if a team or variables that describe match's playing intensity, accuracy, performance quality. Our accurately...
The use of machine learning (ML) in soccer allows for the management a large amount data deriving from monitoring sessions and matches. Although rate perceived exertion (RPE), training load (S-RPE), global position system (GPS) are standard methodologies used team sports to assess internal external workload; how workload affects RPE S-RPE remains still unclear. This study explores relationship between both through ML. Data were recorded 22 elite players, 160 35 matches during 2015/2016...
Abstract The exponential increase in the availability of large-scale mobility data has fueled vision smart cities that will transform our lives. truth is we have just scratched surface research challenges should be tackled order to make this a reality. Consequently, there an increasing interest among different communities (ranging from civil engineering computer science) and industrial stakeholders building knowledge discovery pipelines over such sources. At same time, widespread also raises...
In 2020, countries affected by the COVID-19 pandemic implemented various non-pharmaceutical interventions to contrast spread of virus and its impact on their healthcare systems economies. Using Italian data at different geographic scales, we investigate relationship between human mobility, which subsumes many facets population's response changing situation, COVID-19. Leveraging mobile phone from February through September find a striking decrease in mobility flows net reproduction number. We...
The increasing availability of large amounts data and digital footprints has given rise to ambitious research challenges in many fields, which spans from medical research, financial commercial world, people environmental monitoring. Whereas traditional sources census fail capturing actual up-to-date behaviors, Big Data integrate the missing knowledge providing useful hidden information analysts decision makers. With this paper, we focus on identification city events by analyzing mobile phone...
The recent emergence of the so called online social fitness constitutes a good proxy to study patterns underlying success in sport. Through these platforms, users can collect, monitor and share with friends their sport performance, diet, even burned calories, giving an unprecedented opportunity answer very fascinating questions: What are main factors that shape performance? characteristics distinguish successful sportsmen? Can we characterize role influence on behavior? In current work,...
Real world events are intrinsically dynamic and analytic techniques have to take into account this dynamism. This aspect is particularly important on complex network analysis when relations channels for interaction between actors. Sensing technologies open the possibility of doing so sport networks, enabling team performance in a standard environment rules. Useful applications directly related improving playing quality, but can also shed light all forms efforts that relevant work teams,...
Abstract Purpose By analyzing external workloads with machine learning models (ML), it is now possible to predict injuries, but a moderate accuracy. The increment of the prediction ability nowadays mandatory reduce high number false positives. aim this study was investigate if players’ blood sample profiles could increase predictive trained only on training workloads. Method Eighteen elite soccer players competing in Italian league (Serie B) during seasons 2017/2018 and 2018/2019 took part...
Understanding collective mobility patterns is crucial to plan the restart of production and economic activities, which are currently put in stand-by fight diffusion epidemics. In this report, we use mobile phone data infer movements people between Italian provinces municipalities, analyze incoming, outcoming internal flows before during national lockdown (March 9th, 2020) after closure non-necessary productive activities 23th, 2020). The population flow across municipalities enable for...
Assessing the intensity characteristics of specific soccer drills (matches, small-side game, and match-based exercises) could help practitioners to plan training sessions by providing optimal stimulus for every player. In this paper, we propose a data analytics framework assess neuromuscular or metabolic soccer-specific exercise in relation with expected match intensity. GPS describing physical tasks' external during an entire season twenty-eight semi-professional players competing at fourth...
Humans are routinely asked to evaluate the performance of other individuals, separating success from failure and affecting outcomes science education sports. Yet, in many contexts, metrics driving human evaluation process remain unclear. Here we analyse a massive dataset capturing players' evaluations by judges explore perception soccer, world's most popular sport. We use machine learning design an artificial judge which accurately reproduces evaluation, allowing us demonstrate how observers...
Training for success has increasingly become a balance between maintaining high performance standards and avoiding the negative consequences of accumulated fatigue. The aim this study is to develop big data analytics framework predict players’ wellness according external internal workloads performed in previous days. Such useful coaches staff simulate response scheduled training order adapt stimulus fatigue response. 17 players competing Italian championship (Serie A) were recruited study....
The availability of inexpensive tracking devices, such as GPS-enabled gives the opportunity to collect large amounts trajectory data from vehicles. In this context, we are interested in problem generating traffic information time-dependent networks using kind data. This is not trivial since several works literature use strong assumptions on error distribution want drop, proposing a gravitational model method compute road segment average speed Furthermore show how generate travel-time...