Less Is More: Learning Insights From a Single Motion Sensor for Accurate and Explainable Soccer Goalkeeper Kinematics
Less Is More: Learning Insights From a Single Motion Sensor for Accurate and Explainable Soccer Goalkeeper Kinematics
复制标题
少即是多：从单个运动传感器中学习洞察，以实现准确且可解释的足球守门员运动学
DOI：
--
复制
发表时间：
2021
影响因子：
4.3
通讯作者：
Cristian Axenie
中科院分区：
文献类型：
--
作者：
Gheorghe Lisca;C. Prodaniuc;T. Grauschopf;Cristian Axenie
基于现场传感器的足球运动员跟踪解决方案正在兴起，并提供了对球员在训练或比赛期间动态的新见解。然而，并非所有球员的位置都享有同等的特权。守门员的训练和表现评估长期被忽视。了解什么是“最高跳水进行的位置”，为教练和运动员提供了有价值的信息，以提高表现或避免受伤。在目前的研究中，我们专注于一种实用的方法，从守门员运动学中提取见解，为这种分析提供信息。我们证明，从一个单一的运动传感器的信息可以成功地用于学习模式守门员的运动，并提供一个可解释的守门员运动学评估。我们采用了原始数据和四元数数据，并评估了一系列机器学习算法，这些算法可以直接从数据中区分潜水类型（即二元分类）和潜水与其他类型的特定运动（即多类分类）。我们的研究结果表明，XGBoost在考虑原始数据和四元数时的性能优于其他方法，基本上受益于这两种类型的数据。此外，模型的每个预测都伴随着对每个感测到的运动分量如何有助于描述由模型捕获的特定守门员动作的解释。可解释的预测沿着XGboost的有效部署在我们的应用研究中起了决定性作用。我们在第一批实验中使用7名守门员在30分钟长的训练课程中的在线可用数据评估了我们的方法。
On-field sensor-based soccer player tracking solutions are emerging and provide new insights into the dynamics of the player during training or a match. Yet, not all player positions are equally privileged. Goalkeepers’ training and performance assessment were for a long time ignored. Understanding what is “the side of the post where most high dives were performed” provides valuable input for both the trainer and the athlete to improve performance or avoid injuries. In the current study, we focus on a practical methodology to extract insights from goalkeeper kinematics to inform such analytics. We demonstrate that information from a single motion sensor can be successfully used for learning patterns in goalkeeper’s motion and provide an explainable goalkeeper kinematics assessment. We employed raw and quaternions data and we evaluated a series of machine learning algorithms that discriminate dive types (i.e. binary classification) and dives from other types of specific motions (i.e. multi-class classification) directly from the data. Our results demonstrate that XGBoost outperforms other approaches in terms of performance when considering both raw and quaternions, essentially benefiting from both types of data. Additionally, each prediction of the model is accompanied by an explanation of how each sensed motion component contributes to describing a specific goalkeeper’s action captured by the model. The explainable predictions along with the efficient deployment of XGboost were decisive in our applied study. We evaluated our methodology on a first batch of experiments using online available data from 7 goalkeepers during 30 minutes-long training sessions.