Saved in:
Bibliographic Details
Main Authors: Rockstroh, Sarah, Frenzel, Patrick, Matthes, Daniel, Schubert, Kay, Wollburg, David, Fuchs, Mirco
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.08395
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910890671996928
author Rockstroh, Sarah
Frenzel, Patrick
Matthes, Daniel
Schubert, Kay
Wollburg, David
Fuchs, Mirco
author_facet Rockstroh, Sarah
Frenzel, Patrick
Matthes, Daniel
Schubert, Kay
Wollburg, David
Fuchs, Mirco
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08395
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using deep neural networks to detect non-analytically defined expert event labels in canoe sprint force sensor signals
Rockstroh, Sarah
Frenzel, Patrick
Matthes, Daniel
Schubert, Kay
Wollburg, David
Fuchs, Mirco
Computer Vision and Pattern Recognition
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.
title Using deep neural networks to detect non-analytically defined expert event labels in canoe sprint force sensor signals
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.08395