2023
Journal article
Open Access
A survey on deep learning for human mobility
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 predictive power of artificial intelligence, triggered the application of deep learning to human mobility. 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 a taxonomy of mobility tasks, a discussion on the challenges related to each task and how deep learning may overcome the limitations of traditional models, a description of the most relevant solutions to the mobility tasks described above, and the relevant challenges for the future. Our survey is a guide to the leading deep learning solutions to next-location prediction, crowd flow prediction, trajectory generation, and flow 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.Source: ACM computing surveys 55 (2023). doi:10.1145/3485125
DOI: 10.1145/3485125
DOI: 10.48550/arxiv.2012.02825
Project(s): SoBigData-PlusPlus
Metrics:
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 predictive power of artificial intelligence, triggered the application of deep learning to human mobility. 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 a taxonomy of mobility tasks, a discussion on the challenges related to each task and how deep learning may overcome the limitations of traditional models, a description of the most relevant solutions to the mobility tasks described above, and the relevant challenges for the future. Our survey is a guide to the leading deep learning solutions to next-location prediction, crowd flow prediction, trajectory generation, and flow 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.Source: ACM computing surveys 55 (2023). doi:10.1145/3485125
DOI: 10.1145/3485125
DOI: 10.48550/arxiv.2012.02825
Project(s): SoBigData-PlusPlus
Metrics:
See at:
arXiv.org e-Print Archive 
| ACM Computing Surveys | ISTI Repository | dl.acm.org 
| ACM Computing Surveys | doi.org | CNR ExploRA
2023
Journal article
Open Access
A dataset to assess mobility changes in Chile following local quarantines
Pappalardo L., Cornacchia G., Navarro V., Bravo L., Ferres L.
Fighting the COVID-19 pandemic, most countries have implemented non-pharmaceutical interventions like wearing masks, physical distancing, lockdown, and travel restrictions. Because of their economic and logistical effects, tracking mobility changes during quarantines is crucial in assessing their efficacy and predicting the virus spread. Unlike many other heavily affected countries, Chile implemented quarantines at a more localized level, shutting down small administrative zones, rather than the whole country or large regions. Given the non-obvious effects of these localized quarantines, tracking mobility becomes even more critical in Chile. To assess the impact on human mobility of the localized quarantines, we analyze a mobile phone dataset made available by Telefónica Chile, which comprises 31 billion eXtended Detail Records and 5.4 million users covering the period February 26th to September 20th, 2020. From these records, we derive three epidemiologically relevant metrics describing the mobility within and between comunas. The datasets made available may be useful to understand the effect of localized quarantines in containing the COVID-19 pandemic.Source: Scientific data 10 (2023). doi:10.1038/s41597-022-01893-3
DOI: 10.1038/s41597-022-01893-3
Project(s): SoBigData-PlusPlus
Metrics:
Pappalardo L., Cornacchia G., Navarro V., Bravo L., Ferres L.
Fighting the COVID-19 pandemic, most countries have implemented non-pharmaceutical interventions like wearing masks, physical distancing, lockdown, and travel restrictions. Because of their economic and logistical effects, tracking mobility changes during quarantines is crucial in assessing their efficacy and predicting the virus spread. Unlike many other heavily affected countries, Chile implemented quarantines at a more localized level, shutting down small administrative zones, rather than the whole country or large regions. Given the non-obvious effects of these localized quarantines, tracking mobility becomes even more critical in Chile. To assess the impact on human mobility of the localized quarantines, we analyze a mobile phone dataset made available by Telefónica Chile, which comprises 31 billion eXtended Detail Records and 5.4 million users covering the period February 26th to September 20th, 2020. From these records, we derive three epidemiologically relevant metrics describing the mobility within and between comunas. The datasets made available may be useful to understand the effect of localized quarantines in containing the COVID-19 pandemic.Source: Scientific data 10 (2023). doi:10.1038/s41597-022-01893-3
DOI: 10.1038/s41597-022-01893-3
Project(s): SoBigData-PlusPlus
Metrics:
See at:
ISTI Repository | www.nature.com | CNR ExploRA
2023
Journal article
Open Access
Trajectory test-train overlap in next-location prediction datasets
Luca M., Pappalardo L., Lepri B., Barlacchi G.
Next-location prediction, consisting of forecasting a user's location given their historical trajectories, has important implications in several fields, such as urban planning, geo-marketing, and disease spreading. Several predictors have been proposed in the last few years to address it, including last-generation ones based on deep learning. This paper tests the generalization capability of these predictors on public mobility datasets, stratifying the datasets by whether the trajectories in the test set also appear fully or partially in the training set. We consistently discover a severe problem of trajectory overlapping in all analyzed datasets, highlighting that predictors memorize trajectories while having limited generalization capacities. We thus propose a methodology to rerank the outputs of the next-location predictors based on spatial mobility patterns. With these techniques, we significantly improve the predictors' generalization capability, with a relative improvement in the accuracy up to 96.15% on the trajectories that cannot be memorized (i.e., low overlap with the training set).Source: Machine learning (2023). doi:10.1007/s10994-023-06386-x
DOI: 10.1007/s10994-023-06386-x
Project(s): SoBigData-PlusPlus
Metrics:
Luca M., Pappalardo L., Lepri B., Barlacchi G.
Next-location prediction, consisting of forecasting a user's location given their historical trajectories, has important implications in several fields, such as urban planning, geo-marketing, and disease spreading. Several predictors have been proposed in the last few years to address it, including last-generation ones based on deep learning. This paper tests the generalization capability of these predictors on public mobility datasets, stratifying the datasets by whether the trajectories in the test set also appear fully or partially in the training set. We consistently discover a severe problem of trajectory overlapping in all analyzed datasets, highlighting that predictors memorize trajectories while having limited generalization capacities. We thus propose a methodology to rerank the outputs of the next-location predictors based on spatial mobility patterns. With these techniques, we significantly improve the predictors' generalization capability, with a relative improvement in the accuracy up to 96.15% on the trajectories that cannot be memorized (i.e., low overlap with the training set).Source: Machine learning (2023). doi:10.1007/s10994-023-06386-x
DOI: 10.1007/s10994-023-06386-x
Project(s): SoBigData-PlusPlus
Metrics:
See at:
ISTI Repository | link.springer.com | CNR ExploRA
2023
Journal article
Closed Access
Future directions in human mobility science
Pappalardo L., Manley E., Sekara V., Alessandretti L.
We provide a brief review of human mobility science and present three key areas where we expect to see substantial advancements. We start from the mind and discuss the need to better understand how spatial cognition shapes mobility patterns. We then move to societies and argue the importance of better understanding new forms of transportation. We conclude by discussing how algorithms shape mobility behavior and provide useful tools for modelers. Finally, we discuss how progress on these research directions may help us address some of the challenges our society faces today.Source: Nature computational science 3 (2023): 588–600. doi:10.1038/s43588-023-00469-4
DOI: 10.1038/s43588-023-00469-4
Project(s): SoBigData-PlusPlus
Metrics:
Pappalardo L., Manley E., Sekara V., Alessandretti L.
We provide a brief review of human mobility science and present three key areas where we expect to see substantial advancements. We start from the mind and discuss the need to better understand how spatial cognition shapes mobility patterns. We then move to societies and argue the importance of better understanding new forms of transportation. We conclude by discussing how algorithms shape mobility behavior and provide useful tools for modelers. Finally, we discuss how progress on these research directions may help us address some of the challenges our society faces today.Source: Nature computational science 3 (2023): 588–600. doi:10.1038/s43588-023-00469-4
DOI: 10.1038/s43588-023-00469-4
Project(s): SoBigData-PlusPlus
Metrics:
See at:
www.nature.com | CNR ExploRA
2023
Conference article
Open Access
The effects of route randomization on urban emissions
Cornacchia G., Nanni M., Pedreschi D., Pappalardo L.
Routing algorithms typically suggest the fastest path or slight variation to reach a user's desired destination. Although this suggestion at the individual level is undoubtedly advantageous for the user, from a collective point of view, the aggregation of all single suggested paths may result in an increasing impact (e.g., in terms of emissions). In this study, we use SUMO to simulate the effects of incorporating randomness into routing algorithms on emissions, their distribution, and travel time in the urban area of Milan (Italy). Our results reveal that, given the common practice of routing towards the fastest path, a certain level of randomness in routes reduces emissions and travel time. In other words, the stronger the random component in the routes, the more pronounced the benefits upon a certain threshold. Our research provides insight into the potential advantages of considering collective outcomes in routing decisions and highlights the need to explore further the relationship between route randomization and sustainability in urban transportation.Source: SUMO User Conference 2023, pp. 75–87, Berlin, Germany, 02-04/05/2023
DOI: 10.52825/scp.v4i.217
Project(s): SoBigData-PlusPlus
Metrics:
Cornacchia G., Nanni M., Pedreschi D., Pappalardo L.
Routing algorithms typically suggest the fastest path or slight variation to reach a user's desired destination. Although this suggestion at the individual level is undoubtedly advantageous for the user, from a collective point of view, the aggregation of all single suggested paths may result in an increasing impact (e.g., in terms of emissions). In this study, we use SUMO to simulate the effects of incorporating randomness into routing algorithms on emissions, their distribution, and travel time in the urban area of Milan (Italy). Our results reveal that, given the common practice of routing towards the fastest path, a certain level of randomness in routes reduces emissions and travel time. In other words, the stronger the random component in the routes, the more pronounced the benefits upon a certain threshold. Our research provides insight into the potential advantages of considering collective outcomes in routing decisions and highlights the need to explore further the relationship between route randomization and sustainability in urban transportation.Source: SUMO User Conference 2023, pp. 75–87, Berlin, Germany, 02-04/05/2023
DOI: 10.52825/scp.v4i.217
Project(s): SoBigData-PlusPlus
Metrics:
See at:
ISTI Repository | www.tib-op.org | CNR ExploRA
2023
Journal article
Open Access
Mobility constraints in segregation models
Gambetta D., Mauro G., Pappalardo L.
Since the development of the original Schelling model of urban segregation, several enhancements have been proposed, but none have considered the impact of mobility constraints on model dynamics. Recent studies have shown that human mobility follows specific patterns, such as a preference for short distances and dense locations. This paper proposes a segregation model incorporating mobility constraints to make agents select their location based on distance and location relevance. Our findings indicate that the mobility-constrained model produces lower segregation levels but takes longer to converge than the original Schelling model. We identified a few persistently unhappy agents from the minority group who cause this prolonged convergence time and lower segregation level as they move around the grid centre. Our study presents a more realistic representation of how agents move in urban areas and provides a novel and insightful approach to analyzing the impact of mobility constraints on segregation models. We highlight the significance of incorporating mobility constraints when policymakers design interventions to address urban segregation.Source: Scientific reports (Nature Publishing Group) 13 (2023). doi:10.1038/s41598-023-38519-6
DOI: 10.1038/s41598-023-38519-6
DOI: 10.48550/arxiv.2305.10170
Project(s): HumanE-AI-Net, SoBigData-PlusPlus
Metrics:
Gambetta D., Mauro G., Pappalardo L.
Since the development of the original Schelling model of urban segregation, several enhancements have been proposed, but none have considered the impact of mobility constraints on model dynamics. Recent studies have shown that human mobility follows specific patterns, such as a preference for short distances and dense locations. This paper proposes a segregation model incorporating mobility constraints to make agents select their location based on distance and location relevance. Our findings indicate that the mobility-constrained model produces lower segregation levels but takes longer to converge than the original Schelling model. We identified a few persistently unhappy agents from the minority group who cause this prolonged convergence time and lower segregation level as they move around the grid centre. Our study presents a more realistic representation of how agents move in urban areas and provides a novel and insightful approach to analyzing the impact of mobility constraints on segregation models. We highlight the significance of incorporating mobility constraints when policymakers design interventions to address urban segregation.Source: Scientific reports (Nature Publishing Group) 13 (2023). doi:10.1038/s41598-023-38519-6
DOI: 10.1038/s41598-023-38519-6
DOI: 10.48550/arxiv.2305.10170
Project(s): HumanE-AI-Net
, SoBigData-PlusPlus Metrics:
See at:
Scientific Reports | ISTI Repository | www.nature.com | doi.org | CNR ExploRA
2023
Conference article
Open Access
Trustworthy AI at KDD Lab
Giannotti F., Guidotti R., Monreale A., Pappalardo L., Pedreschi D., Pellungrini R., Pratesi F., Rinzivillo S., Ruggieri S., Setzu M., Deluca R.
This document summarizes the activities regarding the development of Responsible AI (Responsible Artificial Intelligence) conducted by the Knowledge Discovery and Data mining group (KDD-Lab), a joint research group of the Institute of Information Science and Technologies "Alessandro Faedo" (ISTI) of the National Research Council of Italy (CNR), the Department of Computer Science of the University of Pisa, and the Scuola Normale Superiore of Pisa.Source: Ital-IA 2023, pp. 388–393, Pisa, Italy, 29-30/05/2023
Project(s): SoBigData-PlusPlus
Giannotti F., Guidotti R., Monreale A., Pappalardo L., Pedreschi D., Pellungrini R., Pratesi F., Rinzivillo S., Ruggieri S., Setzu M., Deluca R.
This document summarizes the activities regarding the development of Responsible AI (Responsible Artificial Intelligence) conducted by the Knowledge Discovery and Data mining group (KDD-Lab), a joint research group of the Institute of Information Science and Technologies "Alessandro Faedo" (ISTI) of the National Research Council of Italy (CNR), the Department of Computer Science of the University of Pisa, and the Scuola Normale Superiore of Pisa.Source: Ital-IA 2023, pp. 388–393, Pisa, Italy, 29-30/05/2023
Project(s): SoBigData-PlusPlus
See at:
ceur-ws.org | ISTI Repository | CNR ExploRA
2023
Conference article
Open Access
Human mobility, AI assistants, and urban emissions: an insidious triangle
Pappalardo L., Bohm M., Cornacchia G., Mauro G., Pedreschi D., Nanni M.
Transportation remains a significant contributor to greenhouse gas emissions, with a substantial proportion originating from road transport and passenger travel in particular. Today, the relationship between transportation and urban emissions is even more complex, given the increasingly prevalent role and the pervasiveness of AI-based GPS navigation systems such as Google Maps and TomTom. While these services offer benefits to individual drivers, they can also exacerbate congestion and increase pollution if too many drivers are directed onto the same route. In this article, we provide two examples from our research group that explore the impact of vehicular transportation and mobility-AI-based applications on urban emissions. By conducting realistic simulations and studying the impact of GPS navigation systems on emissions, we provide insights into the potential for mitigating transportation emissions and developing policies that promote sustainable urban mobility. Our examples demonstrate how vehicle-generated emissions can be reduced and how studying the impact of GPS navigation systems on emissions can lead to unexpected findings. Overall, our analysis suggests that it is crucial to consider the impact of emerging technologies on transportation and emissions, and to develop strategies that promote sustainable mobility while ensuring the optimal use of these tools.Source: Ital-IA 2023: 3rd National Conference on Artificial Intelligence, pp. 585–589, Pisa, Italy, 29-31/05/2023
Project(s): HumanE-AI-Net, SoBigData-PlusPlus
Pappalardo L., Bohm M., Cornacchia G., Mauro G., Pedreschi D., Nanni M.
Transportation remains a significant contributor to greenhouse gas emissions, with a substantial proportion originating from road transport and passenger travel in particular. Today, the relationship between transportation and urban emissions is even more complex, given the increasingly prevalent role and the pervasiveness of AI-based GPS navigation systems such as Google Maps and TomTom. While these services offer benefits to individual drivers, they can also exacerbate congestion and increase pollution if too many drivers are directed onto the same route. In this article, we provide two examples from our research group that explore the impact of vehicular transportation and mobility-AI-based applications on urban emissions. By conducting realistic simulations and studying the impact of GPS navigation systems on emissions, we provide insights into the potential for mitigating transportation emissions and developing policies that promote sustainable urban mobility. Our examples demonstrate how vehicle-generated emissions can be reduced and how studying the impact of GPS navigation systems on emissions can lead to unexpected findings. Overall, our analysis suggests that it is crucial to consider the impact of emerging technologies on transportation and emissions, and to develop strategies that promote sustainable mobility while ensuring the optimal use of these tools.Source: Ital-IA 2023: 3rd National Conference on Artificial Intelligence, pp. 585–589, Pisa, Italy, 29-31/05/2023
Project(s): HumanE-AI-Net
, SoBigData-PlusPlus
See at:
ceur-ws.org | ISTI Repository | CNR ExploRA
2023
Journal article
Open Access
Navigation services and urban sustainability
Cornacchia G., Nanni M., Pedreschi D., Pappalardo L.
The The rise of socio-technical systems in which humans interact with various forms of Artificial Intelligence, including assistants and recommenders, multiplies the possibility for the emergence of large-scale social behavior, possibly with unintended negative consequences. In this work, we discuss a particularly interesting case, i.e., navigation services' impact on urban emissions, showing through simulations that the sum of many individually "optimal" choices may have unintended negative outcomes because such choices influence and interfere with each other on top of shared resources. To prove this point, we demonstrate how the introduction of a random component in the path suggestion phase may help to relieve the effect of collective and individual choices on the urban environment in terms of urban emissions.Source: FLUCTUATION AND NOISE LETTERS (2023). doi:10.1142/S0219477524500160
DOI: 10.1142/s0219477524500160
Metrics:
Cornacchia G., Nanni M., Pedreschi D., Pappalardo L.
The The rise of socio-technical systems in which humans interact with various forms of Artificial Intelligence, including assistants and recommenders, multiplies the possibility for the emergence of large-scale social behavior, possibly with unintended negative consequences. In this work, we discuss a particularly interesting case, i.e., navigation services' impact on urban emissions, showing through simulations that the sum of many individually "optimal" choices may have unintended negative outcomes because such choices influence and interfere with each other on top of shared resources. To prove this point, we demonstrate how the introduction of a random component in the path suggestion phase may help to relieve the effect of collective and individual choices on the urban environment in terms of urban emissions.Source: FLUCTUATION AND NOISE LETTERS (2023). doi:10.1142/S0219477524500160
DOI: 10.1142/s0219477524500160
Metrics:
See at:
ISTI Repository | Fluctuation and Noise Letters | CNR ExploRA
2023
Conference article
Open Access
One-shot traffic assignment with forward-looking penalization
Cornacchia G., Nanni M., Pappalardo L.
Traffic assignment (TA) is crucial in optimizing transportation systems and consists in efficiently assigning routes to a collection of trips. Existing TA algorithms often do not adequately consider realtime traffic conditions, resulting in inefficient route assignments. This paper introduces Metis, a coordinated, one-shot TA algorithm that combines alternative routing with edge penalization and informed route scoring. We conduct experiments in several cities to evaluate the performance of Metis against state-of-the-art oneshot methods. Compared to the best baseline, Metis significantly reduces CO2 emissions by 18% in Milan, 28% in Florence, and 46% in Rome, improving trip distribution considerably while still having low computational time. Our study proposes Metis as a promising solution for optimizing TA and urban transportation systems.Source: SIGSPATIAL '23 - 31st ACM International Conference on Advances in Geographic Information Systems, Hamburg, Germany, 13-16/11/2023
DOI: 10.1145/3589132.3625637
Project(s): HumanE-AI-Net, SoBigData-PlusPlus
Metrics:
Cornacchia G., Nanni M., Pappalardo L.
Traffic assignment (TA) is crucial in optimizing transportation systems and consists in efficiently assigning routes to a collection of trips. Existing TA algorithms often do not adequately consider realtime traffic conditions, resulting in inefficient route assignments. This paper introduces Metis, a coordinated, one-shot TA algorithm that combines alternative routing with edge penalization and informed route scoring. We conduct experiments in several cities to evaluate the performance of Metis against state-of-the-art oneshot methods. Compared to the best baseline, Metis significantly reduces CO2 emissions by 18% in Milan, 28% in Florence, and 46% in Rome, improving trip distribution considerably while still having low computational time. Our study proposes Metis as a promising solution for optimizing TA and urban transportation systems.Source: SIGSPATIAL '23 - 31st ACM International Conference on Advances in Geographic Information Systems, Hamburg, Germany, 13-16/11/2023
DOI: 10.1145/3589132.3625637
Project(s): HumanE-AI-Net
, SoBigData-PlusPlus Metrics:
See at:
dl.acm.org | ISTI Repository | CNR ExploRA
2022
Journal article
Open Access
Understanding peace through the world news
Voukelatou V., Miliou I., Giannotti F., Pappalardo L.
Peace is a principal dimension of well-being and is the way out of inequity and violence. Thus, its measurement has drawn the attention of researchers, policymakers, and peacekeepers. During the last years, novel digital data streams have drastically changed the research in this field. The current study exploits information extracted from a new digital database called Global Data on Events, Location, and Tone (GDELT) to capture peace through the Global Peace Index (GPI). Applying predictive machine learning models, we demonstrate that news media attention from GDELT can be used as a proxy for measuring GPI at a monthly level. Additionally, we use explainable AI techniques to obtain the most important variables that drive the predictions. This analysis highlights each country's profile and provides explanations for the predictions, and particularly for the errors and the events that drive these errors. We believe that digital data exploited by researchers, policymakers, and peacekeepers, with data science tools as powerful as machine learning, could contribute to maximizing the societal benefits and minimizing the risks to peace.Source: EPJ 11 (2022). doi:10.1140/epjds/s13688-022-00315-z
DOI: 10.1140/epjds/s13688-022-00315-z
Project(s): XAI, SoBigData-PlusPlus
Metrics:
Voukelatou V., Miliou I., Giannotti F., Pappalardo L.
Peace is a principal dimension of well-being and is the way out of inequity and violence. Thus, its measurement has drawn the attention of researchers, policymakers, and peacekeepers. During the last years, novel digital data streams have drastically changed the research in this field. The current study exploits information extracted from a new digital database called Global Data on Events, Location, and Tone (GDELT) to capture peace through the Global Peace Index (GPI). Applying predictive machine learning models, we demonstrate that news media attention from GDELT can be used as a proxy for measuring GPI at a monthly level. Additionally, we use explainable AI techniques to obtain the most important variables that drive the predictions. This analysis highlights each country's profile and provides explanations for the predictions, and particularly for the errors and the events that drive these errors. We believe that digital data exploited by researchers, policymakers, and peacekeepers, with data science tools as powerful as machine learning, could contribute to maximizing the societal benefits and minimizing the risks to peace.Source: EPJ 11 (2022). doi:10.1140/epjds/s13688-022-00315-z
DOI: 10.1140/epjds/s13688-022-00315-z
Project(s): XAI
, SoBigData-PlusPlus Metrics:
See at:
epjdatascience.springeropen.com | ISTI Repository | CNR ExploRA
2022
Journal article
Open Access
Blood sample profile helps to injury forecasting in elite soccer players
Rossi A., Pappalardo L., Filetti C., Cintia P.
Purpose: By analyzing external workloads with machine learning models (ML), it is now possible to predict injuries, but with a moderate accuracy. The increment of the prediction ability is nowadays mandatory to reduce the high number of false positives. The aim of this study was to investigate if players' blood sample profiles could increase the predictive ability of the models trained only on external training workloads. Method: Eighteen elite soccer players competing in Italian league (Serie B) during the seasons 2017/2018 and 2018/2019 took part in this study. Players' blood samples parameters (i.e., Hematocrit, Hemoglobin, number of red blood cells, ferritin, and sideremia) were recorded through the two soccer seasons to group them into two main groups using a non-supervised ML algorithm (k-means). Additionally to external workloads data recorded every training or match day using a GPS device (K-GPS 10 Hz, K-Sport International, Italy), this grouping was used as a predictor for injury risk. The goodness of ML models trained were tested to assess the influence of blood sample profile to injury prediction. Results: Hematocrit, Hemoglobin, number of red blood cells, testosterone, and ferritin were the most important features that allowed to profile players and to analyze the response to external workloads for each type of player profile. Players' blood samples' characteristics permitted to personalize the decision-making rules of the ML models based on external workloads reaching an accuracy of 63%. This approach increased the injury prediction ability of about 15% compared to models that take into consideration only training workloads' features. The influence of each external workload varied in accordance with the players' blood sample characteristics and the physiological demands of a specific period of the season. Conclusion: Field experts should hence not only monitor the external workloads to assess the status of the players, but additional information derived from individuals' characteristics permits to have a more complete overview of the players well-being. In this way, coaches could better personalize the training program maximizing the training effect and minimizing the injury risk.Source: Sport sciences for health (Testo stamp.) (2022). doi:10.1007/s11332-022-00932-1
DOI: 10.1007/s11332-022-00932-1
Project(s): SoBigData-PlusPlus
Metrics:
Rossi A., Pappalardo L., Filetti C., Cintia P.
Purpose: By analyzing external workloads with machine learning models (ML), it is now possible to predict injuries, but with a moderate accuracy. The increment of the prediction ability is nowadays mandatory to reduce the high number of false positives. The aim of this study was to investigate if players' blood sample profiles could increase the predictive ability of the models trained only on external training workloads. Method: Eighteen elite soccer players competing in Italian league (Serie B) during the seasons 2017/2018 and 2018/2019 took part in this study. Players' blood samples parameters (i.e., Hematocrit, Hemoglobin, number of red blood cells, ferritin, and sideremia) were recorded through the two soccer seasons to group them into two main groups using a non-supervised ML algorithm (k-means). Additionally to external workloads data recorded every training or match day using a GPS device (K-GPS 10 Hz, K-Sport International, Italy), this grouping was used as a predictor for injury risk. The goodness of ML models trained were tested to assess the influence of blood sample profile to injury prediction. Results: Hematocrit, Hemoglobin, number of red blood cells, testosterone, and ferritin were the most important features that allowed to profile players and to analyze the response to external workloads for each type of player profile. Players' blood samples' characteristics permitted to personalize the decision-making rules of the ML models based on external workloads reaching an accuracy of 63%. This approach increased the injury prediction ability of about 15% compared to models that take into consideration only training workloads' features. The influence of each external workload varied in accordance with the players' blood sample characteristics and the physiological demands of a specific period of the season. Conclusion: Field experts should hence not only monitor the external workloads to assess the status of the players, but additional information derived from individuals' characteristics permits to have a more complete overview of the players well-being. In this way, coaches could better personalize the training program maximizing the training effect and minimizing the injury risk.Source: Sport sciences for health (Testo stamp.) (2022). doi:10.1007/s11332-022-00932-1
DOI: 10.1007/s11332-022-00932-1
Project(s): SoBigData-PlusPlus
Metrics:
See at:
link.springer.com | ISTI Repository | CNR ExploRA
2022
Journal article
Open Access
Gross polluters and vehicle emissions reduction
Bohm M., Nanni M., Pappalardo L.
Vehicle emissions produce an important share of a city's air pollution, with a substantial impact on the environment and human health. Traditional emission estimation methods use remote sensing stations, missing the full driving cycle of vehicles, or focus on a few vehicles. We have used GPS traces and a microscopic model to analyse the emissions of four air pollutants from thousands of private vehicles in three European cities. We found that the emissions across the vehicles and roads are well approximated by heavy-tailed distributions and thus discovered the existence of gross polluters, vehicles responsible for the greatest quantity of emissions, and grossly polluted roads, which suffer the greatest amount of emissions. Our simulations show that emissions reduction policies targeting gross polluters are far more effective than those limiting circulation based on an uninformed choice of vehicles. Our study contributes to shaping the discussion on how to measure emissions with digital data.Source: Nature sustainability (2022). doi:10.1038/s41893-022-00903-x
DOI: 10.1038/s41893-022-00903-x
Project(s): Track and Know, HumanE-AI-Net , SoBigData-PlusPlus
Metrics:
Bohm M., Nanni M., Pappalardo L.
Vehicle emissions produce an important share of a city's air pollution, with a substantial impact on the environment and human health. Traditional emission estimation methods use remote sensing stations, missing the full driving cycle of vehicles, or focus on a few vehicles. We have used GPS traces and a microscopic model to analyse the emissions of four air pollutants from thousands of private vehicles in three European cities. We found that the emissions across the vehicles and roads are well approximated by heavy-tailed distributions and thus discovered the existence of gross polluters, vehicles responsible for the greatest quantity of emissions, and grossly polluted roads, which suffer the greatest amount of emissions. Our simulations show that emissions reduction policies targeting gross polluters are far more effective than those limiting circulation based on an uninformed choice of vehicles. Our study contributes to shaping the discussion on how to measure emissions with digital data.Source: Nature sustainability (2022). doi:10.1038/s41893-022-00903-x
DOI: 10.1038/s41893-022-00903-x
Project(s): Track and Know
, HumanE-AI-Net , SoBigData-PlusPlus Metrics:
See at:
ISTI Repository | www.nature.com | CNR ExploRA
2022
Journal article
Open Access
Wellness forecasting by external and internal workloads in elite soccer players: a machine learning approach
Rossi A., Perri E., Pappalardo L., Cintia P., Alberti G., Norman D., Iaia F. M.
Training for success has increasingly become a balance between maintaining high performance standards and avoiding the negative consequences of accumulated fatigue. The aim of this study is to develop a big data analytics framework to predict players' wellness according to the external and internal workloads performed in previous days. Such a framework is useful for coaches and staff to simulate the players' response to scheduled training in order to adapt the training stimulus to the players' fatigue response. 17 players competing in the Italian championship (Serie A) were recruited for this study. Players' Global Position System (GPS) data was recorded during each training and match. Moreover, every morning each player has filled in a questionnaire about their perceived wellness (WI) that consists of a 7-point Likert scale for 4 items (fatigue, sleep, stress, and muscle soreness). Finally, the rate of perceived exertion (RPE) was used to assess the effort performed by the players after each training or match. The main findings of this study are that it is possible to accurately estimate players' WI considering their workload history as input. The machine learning framework proposed in this study is useful for sports scientists, athletic trainers, and coaches to maximise the periodization of the training based on the physiological requests of a specific period of the season.Source: Frontiers in physiology 13 (2022). doi:10.3389/fphys.2022.896928
DOI: 10.3389/fphys.2022.896928
Project(s): SoBigData-PlusPlus
Metrics:
Rossi A., Perri E., Pappalardo L., Cintia P., Alberti G., Norman D., Iaia F. M.
Training for success has increasingly become a balance between maintaining high performance standards and avoiding the negative consequences of accumulated fatigue. The aim of this study is to develop a big data analytics framework to predict players' wellness according to the external and internal workloads performed in previous days. Such a framework is useful for coaches and staff to simulate the players' response to scheduled training in order to adapt the training stimulus to the players' fatigue response. 17 players competing in the Italian championship (Serie A) were recruited for this study. Players' Global Position System (GPS) data was recorded during each training and match. Moreover, every morning each player has filled in a questionnaire about their perceived wellness (WI) that consists of a 7-point Likert scale for 4 items (fatigue, sleep, stress, and muscle soreness). Finally, the rate of perceived exertion (RPE) was used to assess the effort performed by the players after each training or match. The main findings of this study are that it is possible to accurately estimate players' WI considering their workload history as input. The machine learning framework proposed in this study is useful for sports scientists, athletic trainers, and coaches to maximise the periodization of the training based on the physiological requests of a specific period of the season.Source: Frontiers in physiology 13 (2022). doi:10.3389/fphys.2022.896928
DOI: 10.3389/fphys.2022.896928
Project(s): SoBigData-PlusPlus
Metrics:
See at:
Frontiers in Physiology | ISTI Repository | www.frontiersin.org | CNR ExploRA
2022
Journal article
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 datasets, such as tracks generated by GPS devices, call detail records, and geo-tagged posts from social media platforms. These datasets have fostered a vast scientific production on various applications of 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. 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. In this paper, 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 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 statistical patterns to assessing the privacy risk related to the analysis of mobility datasets.Source: Journal of statistical software (2022). doi:10.18637/jss.v103.i04
DOI: 10.18637/jss.v103.i04
Project(s): Track and Know, SoBigData-PlusPlus
Metrics:
Pappalardo L., Simini F., Barlacchi G., Pellungrini R.
The last decade has witnessed the emergence of massive mobility datasets, such as tracks generated by GPS devices, call detail records, and geo-tagged posts from social media platforms. These datasets have fostered a vast scientific production on various applications of 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. 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. In this paper, 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 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 statistical patterns to assessing the privacy risk related to the analysis of mobility datasets.Source: Journal of statistical software (2022). doi:10.18637/jss.v103.i04
DOI: 10.18637/jss.v103.i04
Project(s): Track and Know
, SoBigData-PlusPlus Metrics:
See at:
Journal of Statistical Software | ISTI Repository | www.jstatsoft.org | CNR ExploRA
2022
Conference article
Open Access
Enhancing crowd flow prediction in various spatial and temporal granularities
Cardia M., Luca M., Pappalardo L.
The diffusion of the Internet of Things allows nowadays to sense human mobility in great detail, fostering human mobility studies and their applications in various contexts, from traffic management to public security and computational epidemiology. A mobility task that is becoming prominent is crowd flow prediction, i.e., forecasting aggregated incoming and outgoing flows in the locations of a geographic region. Although several deep learning approaches have been proposed to solve this problem, their usage is limited to specific types of spatial tessellations and cannot provide sufficient explanations of their predictions. We propose CrowdNet, a solution to crowd flow prediction based on graph convolutional networks. Compared with state-of-the-art solutions, CrowdNet can be used with regions of irregular shapes and provide meaningful explanations of the predicted crowd flows. We conduct experiments on public data varying the spatio-temporal granularity of crowd flows to show the superiority of our model with respect to existing methods, and we investigate CrowdNet's reliability to missing or noisy input data. Our model is a step forward in the design of reliable deep learning models to predict and explain human displacements in urban environments.Source: WWW '22: The ACM Web Conference 2022, pp. 1251–1259, Virtual Event, Lyon, France, 25-29/04/2022
DOI: 10.1145/3487553.3524851
Project(s): SoBigData-PlusPlus
Metrics:
Cardia M., Luca M., Pappalardo L.
The diffusion of the Internet of Things allows nowadays to sense human mobility in great detail, fostering human mobility studies and their applications in various contexts, from traffic management to public security and computational epidemiology. A mobility task that is becoming prominent is crowd flow prediction, i.e., forecasting aggregated incoming and outgoing flows in the locations of a geographic region. Although several deep learning approaches have been proposed to solve this problem, their usage is limited to specific types of spatial tessellations and cannot provide sufficient explanations of their predictions. We propose CrowdNet, a solution to crowd flow prediction based on graph convolutional networks. Compared with state-of-the-art solutions, CrowdNet can be used with regions of irregular shapes and provide meaningful explanations of the predicted crowd flows. We conduct experiments on public data varying the spatio-temporal granularity of crowd flows to show the superiority of our model with respect to existing methods, and we investigate CrowdNet's reliability to missing or noisy input data. Our model is a step forward in the design of reliable deep learning models to predict and explain human displacements in urban environments.Source: WWW '22: The ACM Web Conference 2022, pp. 1251–1259, Virtual Event, Lyon, France, 25-29/04/2022
DOI: 10.1145/3487553.3524851
Project(s): SoBigData-PlusPlus
Metrics:
See at:
ISTI Repository | dl.acm.org | CNR ExploRA
2022
Journal article
Open Access
Generating mobility networks with generative adversarial networks
Mauro G., Luca M., Longa A., Lepri B., Pappalardo L.
The increasingly crucial role of human displacements in complex societal phenomena, such as traffic congestion, segregation, and the diffusion of epidemics, is attracting the interest of scientists from several disciplines. In this article, we address mobility network generation, i.e., generating a city's entire mobility network, a weighted directed graph in which nodes are geographic locations and weighted edges represent people's movements between those locations, thus describing the entire mobility set flows within a city. Our solution is MoGAN, a model based on Generative Adversarial Networks (GANs) to generate realistic mobility networks. We conduct extensive experiments on public datasets of bike and taxi rides to show that MoGAN outperforms the classical Gravity and Radiation models regarding the realism of the generated networks. Our model can be used for data augmentation and performing simulations and what-if analysis.Source: EPJ 11 (2022). doi:10.1140/epjds/s13688-022-00372-4
DOI: 10.1140/epjds/s13688-022-00372-4
Project(s): SoBigData-PlusPlus
Metrics:
Mauro G., Luca M., Longa A., Lepri B., Pappalardo L.
The increasingly crucial role of human displacements in complex societal phenomena, such as traffic congestion, segregation, and the diffusion of epidemics, is attracting the interest of scientists from several disciplines. In this article, we address mobility network generation, i.e., generating a city's entire mobility network, a weighted directed graph in which nodes are geographic locations and weighted edges represent people's movements between those locations, thus describing the entire mobility set flows within a city. Our solution is MoGAN, a model based on Generative Adversarial Networks (GANs) to generate realistic mobility networks. We conduct extensive experiments on public datasets of bike and taxi rides to show that MoGAN outperforms the classical Gravity and Radiation models regarding the realism of the generated networks. Our model can be used for data augmentation and performing simulations and what-if analysis.Source: EPJ 11 (2022). doi:10.1140/epjds/s13688-022-00372-4
DOI: 10.1140/epjds/s13688-022-00372-4
Project(s): SoBigData-PlusPlus
Metrics:
See at:
EPJ Data Science | epjdatascience.springeropen.com | ISTI Repository | CNR ExploRA
2022
Conference article
Open Access
Connected vehicle simulation framework for parking occupancy prediction (demo paper)
Resce P., Vorwerk L., Han Z., Cornacchia G., Alamdari O. I., Nanni M., Pappalardo L., Weimer D., Liu Y.
This paper demonstrates a simulation framework that collects data about connected vehicles' locations and surroundings in a realistic traffic scenario. Our focus lies on the capability to detect parking spots and their occupancy status. We use this data to train machine learning models that predict parking occupancy levels of specific areas in the city center of San Francisco. By comparing their performance to a given ground truth, our results show that it is possible to use simulated connected vehicle data as a base for prototyping meaningful AI-based applications.Source: SIGSPATIAL '22 - 30th International Conference on Advances in Geographic Information Systems, Seattle, Washington, 1-4/11/2022
DOI: 10.1145/3557915.3560995
Project(s): HumanE-AI-Net
Metrics:
Resce P., Vorwerk L., Han Z., Cornacchia G., Alamdari O. I., Nanni M., Pappalardo L., Weimer D., Liu Y.
This paper demonstrates a simulation framework that collects data about connected vehicles' locations and surroundings in a realistic traffic scenario. Our focus lies on the capability to detect parking spots and their occupancy status. We use this data to train machine learning models that predict parking occupancy levels of specific areas in the city center of San Francisco. By comparing their performance to a given ground truth, our results show that it is possible to use simulated connected vehicle data as a base for prototyping meaningful AI-based applications.Source: SIGSPATIAL '22 - 30th International Conference on Advances in Geographic Information Systems, Seattle, Washington, 1-4/11/2022
DOI: 10.1145/3557915.3560995
Project(s): HumanE-AI-Net
Metrics:
See at:
ISTI Repository | dl.acm.org | doi.org | CNR ExploRA
2022
Conference article
Open Access
How routing strategies impact urban emissions
Cornacchia G., Bohm M., Mauro G., Nanni M., Pedreschi D., Pappalardo L.
Navigation apps use routing algorithms to suggest the best path to reach a user's desired destination. Although undoubtedly useful, navigation apps' impact on the urban environment (e.g., CO2 emissions and pollution) is still largely unclear. In this work, we design a simulation framework to assess the impact of routing algorithms on carbon dioxide emissions within an urban environment. Using APIs from TomTom and OpenStreetMap, we find that settings in which either all vehicles or none of them follow a navigation app's suggestion lead to the worst impact in terms of CO2 emissions. In contrast, when just a portion (around half) of vehicles follow these suggestions, and some degree of randomness is added to the remaining vehicles' paths, we observe a reduction in the overall CO2 emissions over the road network. Our work is a first step towards designing next-generation routing principles that may increase urban well-being while satisfying individual needs.Source: SIGSPATIAL '22 - 30th International Conference on Advances in Geographic Information Systems, Seattle, Washington, 1-4/11/2022
DOI: 10.1145/3557915.3560977
DOI: 10.48550/arxiv.2207.01456
Project(s): SoBigData-PlusPlus
Metrics:
Cornacchia G., Bohm M., Mauro G., Nanni M., Pedreschi D., Pappalardo L.
Navigation apps use routing algorithms to suggest the best path to reach a user's desired destination. Although undoubtedly useful, navigation apps' impact on the urban environment (e.g., CO2 emissions and pollution) is still largely unclear. In this work, we design a simulation framework to assess the impact of routing algorithms on carbon dioxide emissions within an urban environment. Using APIs from TomTom and OpenStreetMap, we find that settings in which either all vehicles or none of them follow a navigation app's suggestion lead to the worst impact in terms of CO2 emissions. In contrast, when just a portion (around half) of vehicles follow these suggestions, and some degree of randomness is added to the remaining vehicles' paths, we observe a reduction in the overall CO2 emissions over the road network. Our work is a first step towards designing next-generation routing principles that may increase urban well-being while satisfying individual needs.Source: SIGSPATIAL '22 - 30th International Conference on Advances in Geographic Information Systems, Seattle, Washington, 1-4/11/2022
DOI: 10.1145/3557915.3560977
DOI: 10.48550/arxiv.2207.01456
Project(s): SoBigData-PlusPlus
Metrics:
See at:
arXiv.org e-Print Archive | ISTI Repository | dl.acm.org | doi.org | doi.org | CNR ExploRA
2022
Journal article
Open Access
Extended energy-expenditure model in soccer: evaluating player performance in the context of the game
Skoki A., Rossi A., Cintia P., Pappalardo L., Stajduhar I.
Every soccer game influences each player's performance differently. Many studies have tried to explain the influence of different parameters on the game; however, none went deeper into the core and examined it minute-by-minute. The goal of this study is to use data derived from GPS wearable devices to present a new framework for performance analysis. A player's energy expenditure is analyzed using data analytics and K-means clustering of low-, middle-, and high-intensity periods distributed in 1 min segments. Our framework exhibits a higher explanatory power compared to usual game metrics (e.g., high-speed running and sprinting), explaining 45.91% of the coefficient of variation vs. 21.32% for high-, 30.66% vs. 16.82% for middle-, and 24.41% vs. 19.12% for low-intensity periods. The proposed methods enable deeper game analysis, which can help strength and conditioning coaches and managers in gaining better insights into the players' responses to various game situations.Source: Sensors (Basel) 22 (2022). doi:10.3390/s22249842
DOI: 10.3390/s22249842
Metrics:
Skoki A., Rossi A., Cintia P., Pappalardo L., Stajduhar I.
Every soccer game influences each player's performance differently. Many studies have tried to explain the influence of different parameters on the game; however, none went deeper into the core and examined it minute-by-minute. The goal of this study is to use data derived from GPS wearable devices to present a new framework for performance analysis. A player's energy expenditure is analyzed using data analytics and K-means clustering of low-, middle-, and high-intensity periods distributed in 1 min segments. Our framework exhibits a higher explanatory power compared to usual game metrics (e.g., high-speed running and sprinting), explaining 45.91% of the coefficient of variation vs. 21.32% for high-, 30.66% vs. 16.82% for middle-, and 24.41% vs. 19.12% for low-intensity periods. The proposed methods enable deeper game analysis, which can help strength and conditioning coaches and managers in gaining better insights into the players' responses to various game situations.Source: Sensors (Basel) 22 (2022). doi:10.3390/s22249842
DOI: 10.3390/s22249842
Metrics:
See at:
Sensors | ISTI Repository | www.mdpi.com | CNR ExploRA