Research on the physical training of athletes in ice and snow sports based on big data

Abstract

Abstract Through big data technology, we analyze the effect of functional fitness training on the physical quality of cross-country skiers and explore a scientific training method suitable for cross-country skiers. The MCDM-Apriori algorithm is proposed based on matrix compression, partitioning, and subsumption to solve the problem that the Apriori algorithm continuously generates the candidate set of intermediate processes during the operation and scans the original database several times, which causes huge consumption to the computer. The HDWA-Kmeans algorithm was used to analyze the effect of experimental training on the physical quality of athletes before and after the training, and the MCDM-Apriori algorithm was used to analyze the quality of functional movements to demonstrate the effect of functional training on the physical quality of cross-country skiers. In the physical quality comparison, the increase of 15 quality indexes in the experimental group was greater than that in the control group except for the push-up strength exhaustion, in which the increase of 49.91% and 54.05% in the experimental group of single-leg squat left and single-leg squat right, respectively. The increase in the quality of movement screening indexes compared with the experimental group, except for the deep squat, all other movements were increased to varying degrees, including a 20.77% increase in quadriceps rotation stability, while the increase in the control group was much worse than the experimental group. The results indicate that the functional training method and the training intensity and volume are consistent with and adapted to the physical training needs and physical characteristics of the athletes in the experimental group.