基于云计算的高校体育负重力量训练数据建模分析

Data modeling and analysis of college sports load-bearing strength training based on cloud computing

负重力量训练模式与受试者训练时的生理生化指标之间存在十分复杂的关联性,采用传统的数据建模方法,难以描述负重训练模式对受试者身体机能的影响,存在时间开销大、预测精度低等问题.针对上述问题,提出一种基于云计算的高校体育负重力量训练数据建模方法.根据运动生理学原理对筛选的5名高校运动员采用肌电采集系统、等动测力系统等实地测试运动员在负重训练周期内体能变化的实际数据,通过生化监测系统,追踪运动员在负重训练周期内生理生化指标的变化情况,科学评价负重训练模式对运动员身体机能的影响,准确评估运动员的体能状况,将评估结果输入到极限学习机中构建体育负重力量训练数据模型.实验结果表明,所提方法与传统的建模方法相比,具有更高的预测精度,模型的均方误差仅为0.22,对体育负重力量训练数据的全面建模分析具有重要的指导意义.

There is a very complicated correlation between the weight training mode and the physiological and biochemical indexes of the subjects.It is difficult to describe the impact of the weight training mode on the body function of the subject using traditional data modeling methods.Problems with low prediction accuracy.Aiming at the above problems,this paper proposes a cloud computing-based data modeling method for college sports weight training.According to the principles of exercise physiology,the five college athletes were selected to use the EMG acquisition system and the isokinetic force measurement system to test the actual data of the athletes’physical fitness changes during the weight training period.Through the biochemical monitoring system,the athletes were tracked during the weight training period.The changes of biochemical indicators,scientific evaluation of the impact of weight-bearing training mode on athletes’physical function,accurate evaluation of athletes’physical condition,and input of evaluation results into extreme learning machine to construct sports weight training data model.The experimental results show that compared with the traditional modeling method,the proposed method has higher prediction accuracy,and the mean square error of the model is only 0.22.It has important guiding significance for the comprehensive modeling and analysis of sports weight training data.