Jeon Minsoo, Lim Hyosung
Department of International Sport, Dankook University, Chungcheongnam-do, Korea.
Department of Physical Education, Anyang University, Incheon, Korea.
BMC Sports Sci Med Rehabil. 2024 May 21;16(1):115. doi: 10.1186/s13102-024-00906-5.
Purpose In this study, the purpose of this study is to identify the determinants of winning and losing in taekwondo by applying decision tree analysis, one of the data mining techniques, based on the 2022 World taekwondo championships women's competition.
272 women's games in the taekwondo championships in Guadalajara held by the WT in 2022 were used. For data processing, an independent sample t-test was performed for differences in game content variables according to the win/lose group, and a decision tree analysis was performed to confirm game content variables affecting the win/lose group. To check the predictive power of the model, classification accuracy, standard error, and misclassification estimates were calculated. All statistical significance levels were set at 0.05.
First, it was found that there was no statistically significant difference only in body attack (attempt) and number of kicking variables according to the winning and losing groups(p > .05), and there were differences in all other game content variables(p < .05). Second, as a result of conducting a decision tree analysis to confirm the determinants of winning and losing in taekwondo sparring, winning situation, tie situation, and number of kicks were identified as important variables.
The World taekwondo championships are analyzed in the currently changed taekwondo competition rules to identify important factors, and at the same time, based on this, data-based coaching is expected to improve performance.
本研究旨在通过应用数据挖掘技术之一的决策树分析，基于2022年世界跆拳道锦标赛女子比赛，确定跆拳道比赛胜负的决定因素。
使用了世界跆拳道联盟（WT）于2022年在瓜达拉哈拉举行的跆拳道锦标赛中的272场女子比赛。在数据处理方面，根据胜负分组对比赛内容变量的差异进行独立样本t检验，并进行决策树分析以确定影响胜负分组的比赛内容变量。为检验模型的预测能力，计算了分类准确率、标准误差和误分类估计值。所有统计显著性水平均设定为0.05。
首先，发现仅身体攻击（尝试）和踢腿次数变量在胜负分组中无统计学显著差异（p＞0.05），而所有其他比赛内容变量存在差异（p＜0.05）。其次，通过进行决策树分析以确定跆拳道对练中胜负的决定因素，获胜情况、平局情况和踢腿次数被确定为重要变量。
在当前变化的跆拳道比赛规则下对世界跆拳道锦标赛进行分析以确定重要因素，同时基于此，预计基于数据的训练将提高成绩。
