Cricket fast bowling detection in a training setting using an inertial measurement unit and machine learning
Cricket fast bowling detection in a training setting using an inertial measurement unit and machine learning
复制标题
DOI：
10.1080/02640414.2018.1553270
复制
发表时间：
2019-06-03
影响因子：
3.4
通讯作者：
Cronin, John
中科院分区：
文献类型：
--
作者：
McGrath, Joseph W.;Neville, Jonathon;Cronin, John
快速投球手过度使用受伤的风险很高。有特定的保龄球频率范围已知有负面或保护作用的快速投球手。惯性测量单元（伊穆斯）可以对运动中的动作进行分类，然而，一些商业产品对于业余运动员来说可能过于昂贵。由于世界上大量的人口可以使用IMU（例如，智能手机），因此在一系列不同的伊穆斯上工作的系统可以增加运动中自动工作负荷监测的可访问性。17名精英快速投球手在训练环境中被用来训练和/或验证五个机器学习模型，通过保龄球和进行防守练习。使用来自所有三个保龄球阶段（分娩前、分娩和分娩后）的数据训练的机器学习模型的准确性与仅使用250 Hz采样率的分娩阶段训练的机器学习模型的准确性进行了比较。接下来，使用下采样到125 Hz、50 Hz和25 Hz的数据训练模型，以模拟较低规格传感器的结果。仅使用交付阶段训练的模型显示出与使用所有三个保龄球阶段训练的模型相似的准确性（> 95%）。当对分娩阶段数据进行下采样时，所有模型和采样频率都保持了准确性（>96%）。
Fast bowlers are at a high risk of overuse injuries. There are specific bowling frequency ranges known to have negative or protective effects on fast bowlers. Inertial measurement units (IMUs) can classify movements in sports, however, some commercial products can betooexpensive for the amateur athlete. As a large number of the world's population has access to an IMU (e.g. smartphones), a system that works on a range of different IMUs may increase the accessibility of automated workload monitoring in sport. Seventeen elite fast bowlers in a training setting were used to train and/or validate five machine learning models by bowling and performing fielding drills. The accuracy of machine learning models trained using data from all three bowling phases (pre-delivery, delivery and post-delivery) were compared to those trained using only the delivery phase at a sampling rate of 250 Hz. Next, models were trained using data down-sampled to 125 Hz, 50 Hz, and 25 Hz to mimic results from lower specification sensors. Models trained using only the delivery phase showed similar accuracy (> 95%) to those trained using all three bowling phases. When delivery-phase data were down-sampled, the accuracy was maintained across all models and sampling frequencies (>96%).