Upper body power (UBP) is one of the most important factors affecting the performance of cross-country skiers during races. Although some initial studies have already attempted to predict UBP, until now, no study has attempted to apply machine learning methods combined with various feature selection algorithms to identify the discriminative features for prediction of UBP. The purpose of this study is to develop new prediction models for predicting the 10-second UBP (UBP10) and 60-second UBP (UBP60) of cross-country skiers by using General Regression Neural Networks (GRNN), Radial-Basis Function Network (RBF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), Single Decision Tree (SDT) and Tree Boost (TB) along with the Relief-F feature selection algorithm, minimum redundancy maximum relevance (mRMR) feature selection algorithm and the Correlation-based Feature Subset Selection (CFS). Several models have been developed to predict UBP10 and UBP60 of cross-country skiers using two datasets. 10-fold cross validation has been performed for model testing. The efficiency of the prediction models has been calculated with their multiple correlation coefficients (R’s), standard error of estimates (SEE’s) and mean absolute percentage errors (MAPE’s). The results emphasize that GRNN-based prediction models show higher performance than the other regression methods. Also, using less number of predictor variables than the full set of predictor variables can be useful for prediction of UBP10 and UBP60 with comparable error rates.

The Handbooks of Sports Medicine and Science present basic clinical and scientific information in a clear style and format as related to specific sports events drawn from the Olympic Summer and Winter Games. Each handbook is written by a small team of authorities co-ordinated by an editor who is internationally respected and recognised in the particular sport activity. Each volume presents up-to-date information on the basic biology of the sport, conditioning techniques, nutrition, and the medical aspects of injury prevention, treatment, and rehabilitation. This Handbook will constitute the most complete and authoritative source of information in existence as regards the scientific and clinical aspects of cross country skiing: physiology, nutrition, biomechanics, injury prevention, treatment and care of medical problems, and conditioning for competition.

"The purpose of the current study was to correlate upper body (UB) lean mass (UBLM), UB maximal strength (UBMS), and average power production during a 3-min ski ergometer (SERG) test to predict the dependent variable, a one-kilometer uphill double pole time trial (DPTT) on snow. We hypothesized UBLM would be most important to performance. All tests were conducted within four weeks of completing the championship phase of a Division I cross country (XC) ski season. Skiers (n=10; all females) performed the mass-start DPTT on snow (i.e., criterion measure), SERG, and UBMS separated by at least a few days recovery. Lastly, body composition was determined via dual-energy x-ray absorptiometry (DXA) with a focus on UB mass characteristics (i.e., trunk + arm lean mass). A significant (p = 0.02) correlation was observed between DPTT and UBLM. No significant (p > 0.05) correlations were observed for UBMS or SERG vs. DPTT. Thus, our hypothesis was supported and we suggest female, competitive cross country skiers work to build functional UB lean mass to best prepare for utilizing the ever popular and evolving double pole technique."--Abstract.