中国组织工程研究

中国组织工程研究 ›› 2023, Vol. 27 ›› Issue (5): 738-744.doi: 10.12307/2023.096

• 组织构建临床实践 clinical practice in tissue construction • 上一篇    下一篇

基于机器学习的速度攀岩关键技术动作指标筛选

游国鹏1，2，王健清3，刘  飞1，袁  强1，柳皓严1，吴  瑛1   

  1. 上海体育学院,1体育教育训练学院，3休闲学院,上海市  200438；2长治医学院公共体育教学部，山西省长治市  046000
  • 收稿日期:2022-01-24 接受日期:2022-04-23 出版日期:2023-02-18 发布日期:2022-07-23
  • 通讯作者: 吴瑛，博士，教授，博士生导师，上海体育学院体育教育训练学院，上海市 200438
  • 作者简介:游国鹏，男，1987年生，河南省洛阳市人，在读博士，副教授，主要从事运动训练学研究。

Screening key technical indicators for speed climbing based on machine learning

You Guopeng1, 2, Wang Jianqing3, Liu Fei1, Yuan Qiang1, Liu Haoyan1, Wu Ying1   

  1. 1School of Physical Education and Training, 3School of Leisure Sport, Shanghai University of Sport, Shanghai 200438, China; 2Department of Physical Education, Changzhi Medical College, Changzhi 046000, Shanxi Province, China
  • Received:2022-01-24 Accepted:2022-04-23 Online:2023-02-18 Published:2022-07-23
  • Contact: Wu Ying, PhD, Professor, Doctoral supervisor, School of Physical Education and Training, Shanghai University of Sport, Shanghai 200438, China
  • About author:You Guopeng, PhD candidate, Associate professor, School of Physical Education and Training, Shanghai University of Sport, Shanghai 200438, China; Department of Physical Education, Changzhi Medical College, Changzhi 046000, Shanxi Province, China

PDF

95

摘要：

文题释义：
随机森林模型：是一个包含多个决策树的分类器，并且其输出的类别是由个别树输出类别的众数而定；主要思想是Bagging并行算法，通过自助采样法对样本集合进行有放回地随机采样，产生M个不同的训练集，从而训练出M个不同的弱学习器，最后将一系列弱学习器进行融合得到强学习器。该模型的优点在于：①很多的数据集上表现良好；②能处理高维度数据，并且不用做特征选择；③训练完后，能够给出哪些feature比较重要；④训练速度快，容易并行化计算。
XGBoost模型：XGBoost是在梯度提升树基础上的改进算法，是以线性分类器或者分类回归树作为基学习器的梯度提升算法；主要思想是Boosting串行生成算法，第i个弱学习器是建立在第i-1个弱学习器的基础上，通过每次弱学习器的学习结果调整每个样本点的权重，使当前误差率大的样本点的权重变大，从而受到下一个弱学习器的重视。迭代进行此步骤，不断更新样本点的权重得到M个弱学习器，并通过融合策略产生强学习器。该模型的优势在于：对损失函数引入正则化项，控制了模型复杂度，防止过拟合；对损失函数进行二阶泰勒展开，提高了收敛速度与收敛精度；引入列抽样，进一步提高计算速度并防止过拟合。

背景：筛选关键动作技术指标用以指导专项训练或比赛是提升比赛成绩的关键。男、女运动员动作技术差异明显，男、女运动员的关键动作技术指标尚未可知。
目的：筛选影响速度攀岩精英运动员比赛成绩的关键动作技术指标，为速度攀岩的科学训练提供方向与理论支撑。
方法：选用2017-2021年间攀岩世锦赛、世界杯和中攀联赛中速度攀岩决赛视频，获取男、女前4名运动员的比赛样本(男子：109 个，女子：117 个)，运用二维运动学分析法，采集运动员的反应时、触点特征和分段速度指标，分别建立男子与女子速度攀岩精英运动员的随机森林和XGBoost回归模型，计算各动作技术指标对比赛成绩影响力。
结果与结论：①男子精英运动员的随机森林和XGBoost模型的均方根误差分别为0.224与0.265，r2分别0.765与0.686；关键动作技术指标为：左手触点时间总和、右手动作频率、右手触点时间总和、3-6号点速度、左脚动作频率、右脚触点时间总和、11-13号点速度、13-18号点速度、8-10号点速度、左脚触点时间总和、左手触点个数和右脚动作频率；②女子精英运动员的随机森林和XGBoost模型的均方根误差分别为0.066与0.055，r2分别为0.846与0.887；关键动作技术指标为：左手触点时间总和、右手触点时间总和、右手动作频率、左脚动作频率、左脚触点时间总和、8-10号点速度、右脚触点时间总和、10-11号点速度和13-18号点速度；③速度攀岩比赛上肢动作技术指标(触点时间总和与动作频率)的影响力高于下肢动作技术指标，触点个数对比赛成绩影响力不高，男子与女子精英运动员首要制胜段落分别为3-6与8-11号点段落。运动员应重点优化首要制胜段落的上肢触点时间，带动优化下肢触点时间指标，提升比赛成绩。

https://orcid.org/0000-0003-4376-9031(游国鹏)；https://orcid.org/0000-0003-4795-0516(吴瑛)

中国组织工程研究杂志出版内容重点：组织构建；骨细胞；软骨细胞；细胞培养；成纤维细胞；血管内皮细胞；骨质疏松；组织工程

关键词: 二维运动学分析, 速度攀岩, 动作技术, 随机森林, XGBoost, 科学训练

Abstract: BACKGROUND: Selecting key technical indicators to guide special training or competition is the key to improving competition performance. There are obvious differences in the techniques of male and female athletes and the key technical indicators of athletes of different sexes have not yet been known.
OBJECTIVE: To select key technical indicators that affect the competition performance of elite speed climbing athletes, thereby providing direction and theoretical support for the scientific training of speed climbing.
METHODS: The videos of speed climbing finals in the 2017-2021 World Championships, World Cup and China Climbing League were selected to obtain the competition samples of the top four male and female athletes (109 men and 117 women). Reaction time, contact time and segmental speed were collected and then random forest and XGBoost models of male and female speed climbing athletes were established using two-dimensional kinematic analysis. Accordingly, the influence of each technical indicator on the competition performance was calculated.
RESULTS AND CONCLUSION: For male athletes, the root-mean-square error values of random forest and XGBoost models were 0.224 and 0.265, respectively, and r2 was 0.765 and 0.686, respectively. The key technical indicators were total contact time of the left hand, motion frequency of the right hand, total contact time of the right hand, speed of holds 3-6, motion frequency of the left foot, total contact time of the right foot, speed of holds 11-13, speed of holds 13-18, speed of holds 8-10, total contact time of the left foot, number of total holds of the left hand and motion frequency of the right foot. For female athletes, the root-mean-square error indicator of random forest and XGBoost models were 0.066 and 0.055, respectively, and r2 were 0.846 and 0.887, respectively. The key technical indicators were total contact time of the left hand, total contact time of the right hand, motion frequency of the right hand, motion frequency of the left foot, total contact time of the left foot, speed of holds 8-10, total contact time of the right foot, and speed of holds 10-11 and 13-18. To conclude, the technical indicators of the upper limbs (contact time sum and action frequency) on speed rock climbing competition are more influential than those of the lower limbs. The number of holds has no high influence on the competition results. The key segments for winning in male and female elite athletes are holds 3-6 and 8-11 respectively. Athletes should focus on optimizing the upper limb contact time of the key segments for winning and then optimize the lower limb contact time, so as to improve the competition performance.

Key words: two-dimensional kinematics analysis, speed climbing, motion technique, random forest, XGBoost, scientific training

中图分类号: