Sports Performance Research Institute New Zealand, AUT University, Auckland, New Zealand.
Manukau Institute of Technology School of Sport, Auckland, New Zealand.
J Sports Sci. 2022 Feb;40(3):323-330. doi: 10.1080/02640414.2021.1993640. Epub 2021 Nov 10.
This study examined whether an inertial measurement unit (IMU) and machine learning models could accurately measure bowling volume (BV), ball release speed (BRS), and perceived intensity zone (PIZ). Forty-four male pace bowlers wore a high measurement range, research-grade IMU (SABELSense) and a consumer-grade IMU (Apple Watch) on both wrists. Each participant bowled 36 deliveries, split into two different PIZs (Zone 1 = 70-85% of maximum bowling effort, Zone 2 = 100% of maximum bowling effort). BRS was measured using a radar gun. Four machine learning models were compared. Gradient boosting models had the best results across all measures (BV: F-score = 1.0; BRS: Mean absolute error = 2.76 km/h; PIZ: F-score = 0.92). There was no significant difference between the SABELSense and Apple Watch on the same hand when measuring BV, BRS, and PIZ. A significant improvement in classifying PIZ was observed for IMUs located on the dominant wrist. For all measures, there was no added benefit of combining IMUs on the dominant and non-dominant wrists.
本研究旨在探讨惯性测量单元（IMU）和机器学习模型是否能准确测量投球量（BV）、球速（BRS）和感知强度区（PIZ）。44 名男性投球手在两只手腕上分别佩戴了高测量范围的研究级 IMU（SABELSense）和消费级 IMU（Apple Watch）。每位参与者投了 36 球，分为两个不同的 PIZ（PIZ1=最大投球强度的 70-85%，PIZ2=最大投球强度的 100%）。BRS 使用雷达枪测量。比较了四种机器学习模型。梯度提升模型在所有指标上的表现都最好（BV：F 分数=1.0；BRS：平均绝对误差=2.76 公里/小时；PIZ：F 分数=0.92）。在测量 BV、BRS 和 PIZ 时，同一只手上的 SABELSense 和 Apple Watch 之间没有显著差异。对于位于优势手腕上的 IMU，PIZ 的分类有显著改善。对于所有指标，在优势手腕和非优势手腕上同时使用 IMU 没有额外的好处。
