Cargando…

Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning

In human activity recognition (HAR), activities are automatically recognized and classified from a continuous stream of input sensor data. Although the scientific community has developed multiple approaches for various sports in recent years, marginal sports are rarely considered. These approaches c...

Descripción completa

Detalles Bibliográficos
Autores principales: Link, Johannes, Perst, Timur, Stoeve, Maike, Eskofier, Bjoern M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9002797/
https://www.ncbi.nlm.nih.gov/pubmed/35408174
http://dx.doi.org/10.3390/s22072560
_version_ 1784685976440799232
author Link, Johannes
Perst, Timur
Stoeve, Maike
Eskofier, Bjoern M.
author_facet Link, Johannes
Perst, Timur
Stoeve, Maike
Eskofier, Bjoern M.
author_sort Link, Johannes
collection PubMed
description In human activity recognition (HAR), activities are automatically recognized and classified from a continuous stream of input sensor data. Although the scientific community has developed multiple approaches for various sports in recent years, marginal sports are rarely considered. These approaches cannot directly be applied to marginal sports, where available data are sparse and costly to acquire. Thus, we recorded and annotated inertial measurement unit (IMU) data containing different types of Ultimate Frisbee throws to investigate whether Convolutional Neural Networks (CNNs) and transfer learning can solve this. The relevant actions were automatically detected and were classified using a CNN. The proposed pipeline reaches an accuracy of 66.6%, distinguishing between nine different fine-grained classes. For the classification of the three basic throwing techniques, we achieve an accuracy of 89.9%. Furthermore, the results were compared to a transfer learning-based approach using a beach volleyball dataset as the source. Even if transfer learning could not improve the classification accuracy, the training time was significantly reduced. Finally, the effect of transfer learning on a reduced dataset, i.e., without data augmentations, is analyzed. While having the same number of training subjects, using the pre-trained weights improves the generalization capabilities of the network, i.e., increasing the accuracy and F1 score. This shows that transfer learning can be beneficial, especially when dealing with small datasets, as in marginal sports, and therefore, can improve the tracking of marginal sports.
format Online
Article
Text
id pubmed-9002797
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90027972022-04-13 Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning Link, Johannes Perst, Timur Stoeve, Maike Eskofier, Bjoern M. Sensors (Basel) Article In human activity recognition (HAR), activities are automatically recognized and classified from a continuous stream of input sensor data. Although the scientific community has developed multiple approaches for various sports in recent years, marginal sports are rarely considered. These approaches cannot directly be applied to marginal sports, where available data are sparse and costly to acquire. Thus, we recorded and annotated inertial measurement unit (IMU) data containing different types of Ultimate Frisbee throws to investigate whether Convolutional Neural Networks (CNNs) and transfer learning can solve this. The relevant actions were automatically detected and were classified using a CNN. The proposed pipeline reaches an accuracy of 66.6%, distinguishing between nine different fine-grained classes. For the classification of the three basic throwing techniques, we achieve an accuracy of 89.9%. Furthermore, the results were compared to a transfer learning-based approach using a beach volleyball dataset as the source. Even if transfer learning could not improve the classification accuracy, the training time was significantly reduced. Finally, the effect of transfer learning on a reduced dataset, i.e., without data augmentations, is analyzed. While having the same number of training subjects, using the pre-trained weights improves the generalization capabilities of the network, i.e., increasing the accuracy and F1 score. This shows that transfer learning can be beneficial, especially when dealing with small datasets, as in marginal sports, and therefore, can improve the tracking of marginal sports. MDPI 2022-03-27 /pmc/articles/PMC9002797/ /pubmed/35408174 http://dx.doi.org/10.3390/s22072560 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Link, Johannes
Perst, Timur
Stoeve, Maike
Eskofier, Bjoern M.
Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning
title Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning
title_full Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning
title_fullStr Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning
title_full_unstemmed Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning
title_short Wearable Sensors for Activity Recognition in Ultimate Frisbee Using Convolutional Neural Networks and Transfer Learning
title_sort wearable sensors for activity recognition in ultimate frisbee using convolutional neural networks and transfer learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9002797/
https://www.ncbi.nlm.nih.gov/pubmed/35408174
http://dx.doi.org/10.3390/s22072560
work_keys_str_mv AT linkjohannes wearablesensorsforactivityrecognitioninultimatefrisbeeusingconvolutionalneuralnetworksandtransferlearning
AT persttimur wearablesensorsforactivityrecognitioninultimatefrisbeeusingconvolutionalneuralnetworksandtransferlearning
AT stoevemaike wearablesensorsforactivityrecognitioninultimatefrisbeeusingconvolutionalneuralnetworksandtransferlearning
AT eskofierbjoernm wearablesensorsforactivityrecognitioninultimatefrisbeeusingconvolutionalneuralnetworksandtransferlearning