Using deep neural networks to detect non-analytically defined expert event labels in canoe sprint force sensor signals
This work addresses the need for automated performance assessment in sports analytics, specifically for canoe sprint athletes and coaches, but it is incremental as it applies existing neural network methods to a new domain.
The paper tackled the problem of automatically detecting paddle stroke cycles in canoe sprint force sensor signals, which typically require manual labeling, and found that a bidirectional gated recurrent unit (BGRU) model was the most effective, with performance assessed using an extended SoftED metric.
Assessing an athlete's performance in canoe sprint is often established by measuring a variety of kinematic parameters during training sessions. Many of these parameters are related to single or multiple paddle stroke cycles. Determining on- and offset of these cycles in force sensor signals is usually not straightforward and requires human interaction. This paper explores convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in terms of their ability to automatically predict these events. In addition, our work proposes an extension to the recently published SoftED metric for event detection in order to properly assess the model performance on time windows. In our results, an RNN based on bidirectional gated recurrent units (BGRUs) turned out to be the most suitable model for paddle stroke detection.