Skip to main content

CORRECTION article

Front. Physiol., 22 July 2024
Sec. Computational Physiology and Medicine

Corrigendum: A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning

  • 1Chengyi College, Jimei University, Xiamen, China
  • 2School of Physical Education and Sport Science, Fujian Normal University, Fuzhou, China
  • 3School of Tourism and Sports Health, Hezhou University, Hezhou, China
  • 4Institute for Sport Business, Loughborough University London, London, United Kingdom

A Corrigendum on
A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning

by Ye X, Huang Y, Bai Z and Wang Y (2023). Front. Physiol. 14:1174525. doi: 10.3389/fphys.2023.1174525

In the published article, there was an error in Materials and methods, Data processing, paragraph five. A correction has been made to the penultimate sentence, which previously stated: “The sampling ratio is set according to the sample imbalance rate.”

The corrected sentence appears below:

“The sampling ratio is set according to the sample balance rate.”

In the published article, there was an error in Materials and methods, Model architecture. A correction has been made to the fourth sentence of paragraph two and the ninth sentence of paragraph four. These sentences previously stated: “The initial learning rate of the adadelta optimizer was set to 0.01.”

The corrected sentence appears below:

“The initial learning rate of the adadelta optimizer was set to 1.0 with a decay rate of 0.95.”

In the published article, there was an error in Materials and methods, Model architecture, paragraph five. A correction has been made to the penultimate sentence, which previously stated: “This study set α to 0.55 and γ to 5.”

The corrected sentence appears below:

“This study’s tuning process for α and γ was based on empirical. The α for the optimal model was approximately 0.986 (i.e., 1 minus the ratio of minority samples to the total sample), while γ was set to 3.5.”

The authors apologize for these errors and state that this does not change the scientific conclusions of the article in any way. The original article has been updated.

Publisher’s note

All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.

Keywords: injury prevention, deep learning, time series, injury risk pattern, injury risk prediction

Citation: Ye X, Huang Y, Bai Z and Wang Y (2024) Corrigendum: A novel approach for sports injury risk prediction: based on time-series image encoding and deep learning. Front. Physiol. 15:1441107. doi: 10.3389/fphys.2024.1441107

Received: 30 May 2024; Accepted: 05 July 2024;
Published: 22 July 2024.

Edited and reviewed by:

John D. Imig, University of Arkansas for Medical Sciences, United States

Copyright © 2024 Ye, Huang, Bai and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

*Correspondence: Yuanqi Huang, eXVhbnFpaHVhbmcxOTk3QDE2My5jb20=

These authors have contributed equally to this work

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.