3 71 MACHINE LEARNING SUPPORTING SUBSTITUTIONS IN SOCCER [16] P. E. di Prampero, A. Botter, and C. Osgnach, “The energy cost of sprint running and the role of metabolic power in setting top performances,” Eur. J. Appl. Physiol., vol. 115, no. 3, pp. 451–469, 2015, doi: 10.1007/s00421-014-3086-4. [17] R. Aquino et al., “Influence of Situational Variables, Team Formation, and Playing Position on Match Running Performance and Social Network Analysis in Brazilian Professional Soccer Players,” J. strength Cond. Res., vol. 34, no. 3, pp. 808–817, 2020, doi: 10.1519/JSC.0000000000002725. [18] D. Linke, D. Link, and M. Lames, “Validation of electronic performance and tracking systems EPTS under field conditions,” PLoS One, vol. 13, no. 7, pp. 1–19, 2018, doi: 10.1371/journal.pone.0199519. [19] M. Mohr, P. Krustrup, and J. Bangsbo, “Fatigue in soccer: A brief review,” J. Sports Sci., vol. 23, no. 6, pp. 593–599, 2005, doi: 10.1080/02640410400021286. [20] J. Bangsbo, F. M. Iaia, and P. Krustrup, “Metabolic response and fatigue in soccer.,” Int. J. Sports Physiol. Perform., vol. 2, no. 2, pp. 111–127, 2007, doi: 10.1123/ijspp.2.2.111. [21] P. S. Bradley, W. Sheldon, B. Wooster, P. Olsen, P. Boanas, and P. Krustrup, “High-intensity running in English FA Premier League soccer matches,” J. Sports Sci., vol. 27, no. 2, pp. 159–168, 2009, doi: 10.1080/02640410802512775. [22] C. Osgnach, S. Poser, R. Bernardini, R. Rinaldo, and P. E. Di Prampero, “Energy cost and metabolic power in elite soccer: A new match analysis approach,” Med. Sci. Sports Exerc., vol. 42, no. 1, pp. 170–178, 2010, doi: 10.1249/MSS.0b013e3181ae5cfd. [23] M. Tomczak and E. Tomczak, “The need to report effect size estimates revisited. An overview of some recommended measures of effect size,” Trends Sport Sci., vol. 1, no. 21, pp. 19–25, 2014, [Online]. Available: http://www.wbc.poznan.pl/Content/325867/5_Trends_Vol21_2014_ no1_20.pdf. [24] A. Fernández, S. García, F. Herrera, and N. V. Chawla, “SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary,” J. Artif. Intell. Res., vol. 61, pp. 863–905, 2018, doi: 10.1613/jair.1.11192. [25] T. B. Dijkhuis, F. J. Blaauw, M. W. van Ittersum, H. Velthuijsen, and M. Aiello, “Personalized physical activity coaching: A machine learning approach,” Sensors (Switzerland), vol. 18, no. 2, pp. 1–20, 2018, doi: 10.3390/s18020623. [26] H. Liu, L. Wang, G. Huang, H. Zhang, and W. Mao, “Activity profiles of full-match and substitution players in the 2018 FIFA World Cup,” Eur. J. Sport Sci., vol. 0, no. 0, pp. 1–7, 2019, doi: 10.1080/17461391.2019.1659420. [27] E. Rey, J. Lago-Ballesteros, and A. Padrón-Cabo, “Timing and tactical analysis of player substitutions in the UEFA champions league,” Int. J. Perform. Anal. Sport, vol. 15, no. 3, pp. 840–850, 2015, doi: 10.1080/24748668.2015.11868835. [28] D. B. Coelho et al., “Effect of player substitutions on the intensity of second-half soccer match play,” Rev. Bras. Cineantropometria Desempenho Hum., vol. 14, no. 2, pp. 183–191, 2012, doi: http://dx.doi. org/10.5007/1980-0037.2012v14n2p183. [29] M. A. Hall, “Correlation-based feature selection for machine learning,” Waikato University, New Zealand, 1999. [30] C. Tudor-Locke, L. Burkett, J. P. Reis, B. E. Ainsworth, C. A. Macera, and D. K. Wilson, “How many days of pedometer monitoring predict weekly physical activity in adults?,” Prev. Med. (Baltim)., vol. 40, no. 3, pp.
RkJQdWJsaXNoZXIy MjY0ODMw