Unraveling the secret of Brazilian and Dutch soccer by capturing successful elements of playing style and playing strategies

• Grant number: 19/16253-1
• Support type: Scholarships in Brazil - Post-Doctorate
• Effective date (Start): September 01, 2019
• Effective date (End): October 31, 2021
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Cooperation agreement: Netherlands Organisation for Scientific Research (NWO)
• Principal researcher: Fúlvia de Barros Manchado Gobatto
• Grantee: Allan da Silva Pinto
• Home Institution: Faculdade de Educação Física (FEF). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 16/50250-1 - The secret of playing football: Brazil versus the Netherlands, AP.TEM

Abstract

This research project aims to characterize and predict playing styles and key events of Brazilian and Dutch soccer by capturing successful elements of game play of both countries and by combining the expertise of data science, computer science and sport science. In this context, this research will propose techniques and methods for analyzing data related to the physical and tactical performance of players from Brazilian and Dutch Teams (focusing on successful games). Features of playing styles will be approached from two perspectives. The first concerns features that capture the dynamics of the game and characterize aspects of field training, while the second will focus on the analysis of build-up plays and key events built during the game (e.g., shots on goal, transitions from defenders to midfielders). For comparing playing styles of both countries, the data will be collected in four different age groups in Brazil and the Netherlands during the official games, in order to compare the development of the game between the two countries. The data will be collected by using a local positioning measurement system, for reasons of accuracy and consistency. Finally, this research project will focus on bridging the gap between fundamental science and football practice. In this context, the research results obtained during this project will be implemented in a software to be used by instructors and coaches in order to: decide on their strategy before a game; to analyze the behavior of the player and team during a game to adjust the strategy accordingly; and to choose and create training forms to improve player and team performance.

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CAMPANA, JOSE L. FLORES; PINTO, ALLAN; CORDOVA NEIRA, MANUEL ALBERTO; LORGUS DECKER, LUIS GUSTAVO; SANTOS, ANDREZA; CONCEICAO, JHONATAS S.; TORRES, RICARDO DA SILVA. On the Fusion of Text Detection Results: A Genetic Programming Approach. IEEE ACCESS, v. 8, p. 81257-81270, 2020. Web of Science Citations: 0.

CORDOVA, MANUEL; PINTO, ALLAN; PEDRINI, HELIO; TORRES, RICARDO DA SILVA. Pelee-Text plus plus : A Tiny Neural Network for Scene Text Detection. IEEE ACCESS, v. 8, p. 223172-223188, 2020. Web of Science Citations: 0.

DIAS, DANIELLE; PINTO, ALLAN; DIAS, ULISSES; LAMPARELLI, RUBENS; LE MAIRE, GUERRIC; TORRES, RICARDO DA S. A Multirepresentational Fusion of Time Series for Pixelwise Classification. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, v. 13, p. 4399-4409, 2020. Web of Science Citations: 0.

PINTO, ALLAN; GOLDENSTEIN, SIOME; FERREIRA, ALEXANDRE; CARVALHO, TIAGO; PEDRINI, HELIO; ROCHA, ANDERSON. Leveraging Shape, Reflectance and Albedo From Shading for Face Presentation Attack Detection. IEEE Transactions on Information Forensics and Security, v. 15, p. 3347-3358, 2020. Web of Science Citations: 0.