Intra- and Inter-Seasonal Fitness and Training Load Variations of Elite U20 Soccer Players.

Inherent physical and anthropometric traits of elite soccer players, influenced by nature and nurture, account for the emergence of performances across time. Purpose: The present study aimed to evaluate inter- and intraseasonal differences and the influence of playing position on training and fitness metrics in talented young soccer players. Methods: A total of 74 male players from U20 teams of a single elite club were tested both at beginning, during, and at the end of three consecutive competitive seasons. Players under went anthropometric measurement and were tested for aerobic, jumping, and sprinting performances; the GPS-derived measures of metabolic power (MP) and equivalent distance index (ED) of every athlete were analyzed. Results: Difference between teams emerged in Mognoni's test, while it did not in countermovement jump and anthropometrics. ED was different across seasons. The model selection criteria revealed that the Bosco-Vittori test achieved the best fit. BMI and countermovement jump (CMJ) increased, and fat mass decreased, during season; different intraseasonal trends for CMJ. MP was slightly greater in midfielder. Conclusion: Network approaches in modeling performance metrics in sports team could unveil original interconnections between performance factors. In addition, the authors support multiparametric longitudinal assessments and a huge database of sports data for facilitating talent identification.

Monitoring motor traits of young athletes in Tuscany: a perspective from the first phase of the project "I ragazzi della Toscana 30 anni dopo".

BACKGROUND: The current study represents the preliminary report of an Italian regional project aimed to monitor the status of young athletes in modern times and linking it to the monitoring started in the nineties. METHODS: After the preparatory stage, data were analyzed and discussed with coaches and researchers. Next, for the main stage, the coaches performed the tests and the supervisors reported them in a database. A total number of 173 participants (age: 10.64±2.42 years, BMI=18.43±3.49 kg/m2) were tested for standing long jump, sit and reach, 10×4 Shuttle Run, 3 kg-medical ball throw, and Sergeant Test. Nine sports disciplines were represented. RESULTS: 46.5% of the participants trained more than twice a week and 15.8% of the participants played more than 1 discipline. Girls were more flexible than boys, and differences emerged in the Sergeant and Shuttle Run Test, with boys outperforming girls in older ages. CONCLUSIONS: The "sentinel" role of sports societies, in terms of health and developmental risks, should represent valuable accountability. Authors advocate a specific focus shall be directed to the risks of youth sports specialization, gender-related developmental trajectories, long-life physical activity, and sport engagement.

Vehicular Traffic Congestion Classification by Visual Features and Deep Learning Approaches: A Comparison.

Automatic traffic flow classification is useful to reveal road congestions and accidents. Nowadays, roads and highways are equipped with a huge amount of surveillance cameras, which can be used for real-time vehicle identification, and thus providing traffic flow estimation. This research provides a comparative analysis of state-of-the-art object detectors, visual features, and classification models useful to implement traffic state estimations. More specifically, three different object detectors are compared to identify vehicles. Four machine learning techniques are successively employed to explore five visual features for classification aims. These classic machine learning approaches are compared with the deep learning techniques. This research demonstrates that, when methods and resources are properly implemented and tested, results are very encouraging for both methods, but the deep learning method is the most accurately performing one reaching an accuracy of 99.9% for binary traffic state classification and 98.6% for multiclass classification.

Detection and Validation of Tow-Away Road Sign Licenses through Deep Learning Methods.

This work presents the practical design of a system that faces the problem of identification and validation of private no-parking road signs. This issue is very important for the public city administrations since many people, after receiving a code that identifies the signal at the entrance of their private car garage as valid, forget to renew the code validity through the payment of a city tax, causing large money shortages to the public administration. The goal of the system is twice since, after recognition of the official road sign pattern, its validity must be controlled by extracting the code put in a specific sub-region inside it. Despite a lot of work on the road signs' topic having been carried out, a complete benchmark dataset also considering the particular setting of the Italian law is today not available for comparison, thus the second goal of this work is to provide experimental results that exploit machine learning and deep learning techniques that can be satisfactorily used in industrial applications.