运动员跑步强度训练关节损伤优化预测仿真

发布时间：2018-06-12 18:12

  本文选题：跑步强度训练 + 关节　； 参考：《计算机仿真》2017年11期

【摘要】：对运动员跑步强度训练下关节损伤的优化预测,能够有效提升运动员竞技体育水平。对关节损伤的预测,需要选取对损伤有显著影响的因素作为自变量,计算损伤统计量的显著性筛选变量,完成跑步训练下运动员关节损伤的预测。传统方法分析关节损伤数据源矩阵中元素的统计特性,利用线性特征值统计量作为相关性指标,但忽略了计算出损伤统计量的筛选变量,导致预测精度偏低。提出基于二元Logistic逐步回归分析的跑步强度训练下关节损伤分析方法。建立关节损伤影响因素分析模型,加强训练负荷强度对损伤因素的影响机理和因素间的作用关系,进行运动员关节损伤特征分析,将运动员超负荷训练程度作为因变量,选取对损伤有显著影响的因素作为自变量,计算损伤统计量的显著性筛选变量,对关节损伤进行预测。实验结果表明,所提方法能够有效提升竞技比赛成绩提供了科学依据和指导。
[Abstract]:The optimal prediction of joint injury under intensity training can effectively improve the athletic level of athletes. For the prediction of joint injury, it is necessary to select the factors that have significant influence on the injury as independent variables, calculate the significant screening variables of injury statistics, and complete the prediction of joint injury of athletes under running training. The traditional method is used to analyze the statistical characteristics of the elements in the joint injury data source matrix. The linear eigenvalue statistics are used as the correlation index, but the filtering variables of the damage statistics are neglected, which leads to the low prediction accuracy. A method of joint damage analysis under running intensity training based on binary Logistic stepwise regression analysis was proposed. This paper establishes the analysis model of the influencing factors of joint injury, strengthens the influence mechanism of the training load intensity on the injury factors and the action relationship among the factors, analyzes the characteristics of the athletes joint injury, and takes the training degree of the athletes' overload as the dependent variable. The factors which have significant influence on the injury were selected as independent variables, and the significant screening variables were calculated to predict the joint injury. The experimental results show that the proposed method can effectively improve the performance of competitive competition to provide scientific basis and guidance.
【作者单位】： 平顶山学院体育学院;
【分类号】：G822;O212
，

本文编号：2010612