Research Centre in Sports, Health and Human Development, Covilhã, Portugal.
Department of Sport Sciences, Instituto Politécnico de Bragança, Bragança, Portugal.
PeerJ. 2023 Aug 4;11:e15806. doi: 10.7717/peerj.15806. eCollection 2023.
Applying data-reduction techniques to extract meaningful information from electronic performance and tracking systems (EPTS) has become a hot topic in football training load (TL) monitoring. The aim of this study was to reduce the dimensionality of the internal and external load measures, by a principal component approach, to describe and explain the resultant equations for TL monitoring during a standard in-season microcycle in sub-elite youth football. Additionally, it is intended to identify the most representative measure for each principal component. A principal component analysis (PCA) was conducted with a Monte Carlo parallel analysis and VariMax rotation to extract baseline characteristics, external TL, heart rate (HR)-based measures and perceived exertion. Training data were collected from sixty sub-elite young football players during a 6-week training period using 18 Hz global positioning system (GPS) with inertial sensors, 1 Hz short-range telemetry system, total quality recovery (TQR) and rating of perceived exertion (RPE). Five principal components accounted for 68.7% of the total variance explained in the training data. Resultant equations from PCA was subdivided into: (1) explosiveness, accelerations and impacts (27.4%); (2) high-speed running (16.2%); (3) HR-based measures (10.0%); (4) baseline characteristics (8.3%); and (5) average running velocity (6.7%). Considering the highest factor in each principal component, decelerations (PCA 1), sprint distance (PCA 2), average HR (PCA 3), chronological age (PCA 4) and maximal speed (PCA 5) are the conditional dimension to be considered in TL monitoring during a standard microcycle in sub-elite youth football players. Current research provides the first composite equations to extract the most representative components during a standard in-season microcycle in sub-elite youth football players. Futures research should expand the resultant equations within training days, by considering other well-being measures, technical-tactical skills and match-related contextual factors.
应用数据缩减技术从电子绩效和跟踪系统（EPTS）中提取有意义的信息，已成为足球训练负荷（TL）监测领域的热门话题。本研究的目的是通过主成分方法降低内部和外部负荷测量的维度，以描述和解释在亚精英青年足球的标准赛季微周期中 TL 监测的结果方程。此外，还旨在确定每个主成分的代表性度量。使用蒙特卡罗并行分析和 VariMax 旋转对基线特征、外部 TL、基于心率（HR）的测量值和感知用力进行主成分分析（PCA）。使用具有惯性传感器的 18 Hz 全球定位系统（GPS）、1 Hz 短程遥测系统、总质量恢复（TQR）和感知用力（RPE），在 6 周的训练期间，从 60 名亚精英年轻足球运动员收集训练数据。五个主成分解释了训练数据总方差的 68.7%。PCA 的结果方程分为：（1）爆发性、加速度和冲击力（27.4%）；（2）高速奔跑（16.2%）；（3）基于 HR 的测量值（10.0%）；（4）基线特征（8.3%）；和（5）平均跑动速度（6.7%）。考虑到每个主成分中的最高因素，减速（PCA1）、冲刺距离（PCA2）、平均 HR（PCA3）、年龄（PCA4）和最大速度（PCA5）是在亚精英青年足球运动员标准微周期中进行 TL 监测时要考虑的条件维度。目前的研究提供了在亚精英青年足球运动员标准赛季微周期中提取最具代表性成分的第一个综合方程。未来的研究应该通过考虑其他健康措施、技术战术技能和比赛相关的背景因素，在训练日内扩展结果方程。
