It is increasingly important for professional sports teams to monitor player fitness in order to optimize performance. Models have been put forward linking fitness in training to performance in competition but rely on regular measurements of player fitness. As formal tests for measuring player fitness are typically time-consuming and inconvenient, measurements are taken infrequently. As such, it may be challenging to accurately predict performance in competition as player fitness is unknown. Alternatively, other data, such as how the players are feeling, may be measured more regularly. This data, however, may be biased as players may answer the questions differently and these differences may dominate the data. Linear mixed methods and support vector machines were used to estimate player fitness from available covariates at times when explicit measures of fitness were unavailable. Using data provided by a professional rugby club, a case study was used to illustrate the application and value of these models. Both models performed well with R2 values ranging from 60% to 85%, demonstrating that the models largely captured the biases introduced by individual players.
MaughanR. The athlete’s diet: nutritional goals and dietary strategies. Proc Nutr So2002; 61: 87–96.
2.
JamesT. Science in search of gold. Eng Technol2012; 7: 44–47.
3.
CalvertTBanisterESavageM. A systems model of the effects on training on physical performance. IEEE Trans Syst Man Cybern1976; SMC-6: 94–102.
4.
Calvert TW, Banister EW, Savage MV et al. A systems model of the effects of training on physical performance. IEEE Trans Syst Man Cybern 1976; 2: 94–102.
5.
MortonRFitz-ClarkeJBanisterE. Modeling human performance in running. Appl Physiol1990; 69: 1171–1177.
6.
HellardPAvalosMLacosteL. Assessing the limitations of the banister model in monitoring training. J Sports Sci2006; 24: 509–520.
7.
Scarf P, Shrahili M, Jobson S, et al. Modelling and optimisation of the sport and exercise training process. In: Goossens D, Spieksma F and Scarf P (eds) Proceedings of the 4th International Conference on Mathematics in Sport: MathSport International 2013, Leuven, Belgium, 5–7 June 2013.
8.
Castro-Piñero J, et al. Assessing muscular strength in youth: usefulness of standing long jump as a general index of muscular fitness. J Strength Cond Res 2010; 24: 1810–1817.
9.
MarekSMCramerJTFincherAL. Acute effects of static and proprioceptive neuromuscular facilitation stretching on muscle strength and power output. J Athl Train2005; 40(2): 94.
10.
LarryDI. Comparison of the vertec and just jump systems for measuring height of vertical jump by young children. Percept Mot Skills1998; 86(2): 659–663.
11.
LeeP. Bayesian statistics: An introduction, Chichester, UK: Wiley, 2012.
12.
CristianiniNShawe-TaylorJ. An introduction to support vector machines and other kernel-based learning methods, Cambridge, UK: Cambridge University Press, 2000.
13.
VapnikV. The nature of statistical learning theory, New York, USA: Springer, 1999.
14.
Scholkopf, Simard P, Vapnik V, et al. Improving the accuracy and speed of support vector machines. In: Advances in neural information processing systems 9: Proceedings of the 1996 conference, volume 9, p.375. MIT Press.
15.
MoulinLDa SilvaAAEl-SharkawiM. Support vector machines for transient stability analysis of large-scale power systems. IEEE Trans Power Syst2004; 19(2): 818–825.
16.
Barabino N, Pallavicini M, Petrolini A, et al. Support vector machines vs multi-layer perceptrons in particle identification. In: Proceedings of the European symposium on artifical neural networks’ 99, pp.257–262.
17.
Guo G, Li SZ and Chan K. Face recognition by support vector machines. In: Automatic face and gesture recognition, 2000. Proceedings. fourth IEEE international conference on, pp.196–201. IEEE.
18.
Osuna E, Freund R and Girosit F. Training support vector machines: an application to face detection. In: Computer vision and pattern recognition, 1997. Proceedings., 1997 IEEE computer society conference on, pp.130–136. IEEE.
19.
DruckerHWuDVapnikVN. Support vector machines for spam categorization. IEEE Trans Neural Networks1999; 10(5): 1048–1054.
20.
BrownMPGrundyWNLinD. Knowledge-based analysis of microarray gene expression data by using support vector machines. Proc Natl Acad Sci USA2000; 97(1): 262–267.
21.
WuXKumarVRoss QuinlanJ. Top 10 algorithms in data mining. Knowl Inf Syst2008; 14(1): 1–37.
22.
R Development Core Team. R: A language and environment for statistical computing, Vienna, Austria: R Foundation for Statistical Computing, 2005.
23.
Joachims T. Estimating the generalization performance of a SVM efficiently. Technical report, Universität Dortmund, 2000.
24.
CampbellCCristianiniNShawe-TaylorJ. Dynamically adapting kernels in support vector machines. Adv Neural Inf Process Syst1999; 11: 204–210.
25.
ChapelleOVapnikVBousquetO. Choosing multiple parameters for support vector machines. Mach Learn2002; 46(1): 131–159.
26.
BishopC. Pattern recognition and machine learning2006; Vol. 4; New York: Springer.
27.
WuKWangS. Choosing the kernel parameters for support vector machines by the inter-cluster distance in the feature space. Pattern Recognit2009; 42(5): 710–717.
SchölkopfBSmolaAJWilliamsonRC. New support vector algorithms. Neural Comput2000; 12(5): 1207–1245.
30.
GathercoleRSporerBStellingwerffT. Countermovement jump performance with increased training loads in elite female rugby athletes. Int J Sports Med2015; 36(9): 722–728.
31.
GathercoleRJStellingwerffTSporerBC. Effect of acute fatigue and training adaptation on countermovement jump performance in elite snowboard cross athletes. J Strength Cond Res2015; 29(1): 37–46.
32.
Valentini G and Masulli F. Ensembles of Learning Machines. In: Marinaro M and Tagliaferri R (eds) Neural Nets. WIRN 2002. Lecture Notes in Computer Science, vol 2486. Springer, Berlin, Heidelberg, 2002.
