基于地标点的、从分钟级多模态足球监测数据中区分损伤相关运动员训练/比赛时段
When Minute-Resolution Monitoring Meets Session-Level Injury Labels: Landmark-Based Discrimination in Elite Women's Football
浏览论文内容
中文总结 AI 辅助
该研究针对分钟级监测数据与时段级损伤标签的不匹配问题，提出固定地标点的运动员时段表示方法，结合2020年SoccerMon数据，用多种模型评估了不同表示的损伤区分性能。
中文摘要 AI 辅助
运动员监测数据可在比赛或训练时段内按分钟记录，而损伤信息仅能表明整个时段是否与损伤相关，这造成了建模问题：为每一分钟赋予相同的时段级标签，会暗示损伤状态在每个精确时间点都是已知的，尽管时段内的损伤发生时间是未知的。我们的创新之处在于提出了一种固定地标点、每个运动员时段一个表示的框架，直接解决这种不匹配问题。我们不标记每一分钟，而是利用到每个地标点为止观测到的信息，为每个运动员时段构建一个表示，将目标保持在时段级别，避免了无依据的分钟级损伤监督。地标点是同一时段内的固定时间点，如10、20或30分钟。在每个地标点，我们评估整个时段是否与损伤相关或非损伤相关，并检查随着时段内更多信息的获取，区分度如何变化。使用2020年的SoccerMon数据，我们分析了48名精英女子足球运动员的3743个运动员时段，其中包括5名运动员的22个损伤相关时段。我们通过运动员不相交验证、运动员集群自举不确定性、共同队列敏感性分析、替代负运动员折分配、等运动员加权，以及Logistic Regression、Random Forest和XGBoost基准，评估了赛前、累积、动态和组合表示。主要的CUM+DYN Logistic Regression在各地标点的ROC-AUC为0.367-0.607，PR-AUC为0.0080-0.0150，不确定性范围较宽；含PRE的表示在多个地标点显示出更高的点估计值，但仍存在不确定性。
英文摘要
Minute-resolution athlete monitoring is increasingly common, while injury annotation may exist only at the athlete-session level and omit within-session onset time. Replicating a positive session label across every recorded minute would therefore create unsupported minute-level supervision. We address this label-resolution mismatch using fixed elapsed-time landmarks at 10, 20, 30, 40, 50, and 60 min, constructing one representation per athlete-session from information available up to each landmark while keeping the target as a same-day injury-associated session indicator. Using 2020 SoccerMon data from elite women's football, the modelling cohort contains 2,259 Team A athlete-sessions from 27 athletes, including all 22 positive sessions from five athletes. Evaluation is athlete-disjoint. We compare contextual, cumulative, and dynamic representations; Logistic Regression, Random Forest, XGBoost, and TabPFN; and training-only NONE, SMOTE, and CTGAN conditions. Robustness is assessed using athlete-cluster bootstrap, a fixed common cohort, alternative fold allocations, leave-one-positive-athlete-out analysis, and equal-athlete weighting. Discrimination is landmark-dependent and non-monotonic. TabPFN improves later-landmark discrimination relative to Logistic Regression but does not consistently outperform Random Forest. Synthetic augmentation provides condition-specific rather than universal benefit. The contribution is a unit-aligned framework for using minute-resolution predictors with session-level supervision, not minute-specific injury prediction.
发表机构
- National Technical University of Athens（雅典国立技术大学）
机构由 AI 辅助整理，请以论文原文为准。
