Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities
The educational environment plays a vital role in the development of students who participate in athletic pursuits both in terms of their physical health and their ability to detect fatigue. As a result of recent advancements in deep learning and biosensors benefitting from edge computing resources,...
Published in: | Scientific Reports |
---|---|
Main Author: | |
Format: | Article |
Language: | English |
Published: |
Nature Research
2024
|
Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198348349&doi=10.1038%2fs41598-024-66839-8&partnerID=40&md5=9a0c65bd19ee07017f5eb8852292d017 |
id |
2-s2.0-85198348349 |
---|---|
spelling |
2-s2.0-85198348349 Liu P.; Song Y.; Yang X.; Li D.; Khosravi M. Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities 2024 Scientific Reports 14 1 10.1038/s41598-024-66839-8 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198348349&doi=10.1038%2fs41598-024-66839-8&partnerID=40&md5=9a0c65bd19ee07017f5eb8852292d017 The educational environment plays a vital role in the development of students who participate in athletic pursuits both in terms of their physical health and their ability to detect fatigue. As a result of recent advancements in deep learning and biosensors benefitting from edge computing resources, we are now able to monitor the physiological fatigue of students participating in sports in real time. These devices can then be used to analyze the data using contemporary technology. In this paper, we present an innovative deep learning framework for forecasting fatigue in athletic students following physical exercise. It addresses the issue of lack of precision computational models and extensive data analysis in current approaches to monitoring students’ physical activity. In our study, we classified fatigue and non-fatigue based on photoplethysmography (PPG) signals. Several deep learning models are compared in the study. Using limited training data, determining the optimal parameters for PPG presents a significant challenge. For datasets containing many data points, several models were trained using PPG signals: a deep residual network convolutional neural network (ResNetCNN) ResNetCNN, an Xception architecture, a bidirectional long short-term memory (BILSTM), and a combination of these models. Training and testing datasets were assigned using a fivefold cross validation approach. Based on the testing dataset, the model demonstrated a proper classification accuracy of 91.8%. © The Author(s) 2024. Nature Research 20452322 English Article All Open Access; Gold Open Access |
author |
Liu P.; Song Y.; Yang X.; Li D.; Khosravi M. |
spellingShingle |
Liu P.; Song Y.; Yang X.; Li D.; Khosravi M. Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities |
author_facet |
Liu P.; Song Y.; Yang X.; Li D.; Khosravi M. |
author_sort |
Liu P.; Song Y.; Yang X.; Li D.; Khosravi M. |
title |
Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities |
title_short |
Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities |
title_full |
Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities |
title_fullStr |
Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities |
title_full_unstemmed |
Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities |
title_sort |
Medical intelligence using PPG signals and hybrid learning at the edge to detect fatigue in physical activities |
publishDate |
2024 |
container_title |
Scientific Reports |
container_volume |
14 |
container_issue |
1 |
doi_str_mv |
10.1038/s41598-024-66839-8 |
url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198348349&doi=10.1038%2fs41598-024-66839-8&partnerID=40&md5=9a0c65bd19ee07017f5eb8852292d017 |
description |
The educational environment plays a vital role in the development of students who participate in athletic pursuits both in terms of their physical health and their ability to detect fatigue. As a result of recent advancements in deep learning and biosensors benefitting from edge computing resources, we are now able to monitor the physiological fatigue of students participating in sports in real time. These devices can then be used to analyze the data using contemporary technology. In this paper, we present an innovative deep learning framework for forecasting fatigue in athletic students following physical exercise. It addresses the issue of lack of precision computational models and extensive data analysis in current approaches to monitoring students’ physical activity. In our study, we classified fatigue and non-fatigue based on photoplethysmography (PPG) signals. Several deep learning models are compared in the study. Using limited training data, determining the optimal parameters for PPG presents a significant challenge. For datasets containing many data points, several models were trained using PPG signals: a deep residual network convolutional neural network (ResNetCNN) ResNetCNN, an Xception architecture, a bidirectional long short-term memory (BILSTM), and a combination of these models. Training and testing datasets were assigned using a fivefold cross validation approach. Based on the testing dataset, the model demonstrated a proper classification accuracy of 91.8%. © The Author(s) 2024. |
publisher |
Nature Research |
issn |
20452322 |
language |
English |
format |
Article |
accesstype |
All Open Access; Gold Open Access |
record_format |
scopus |
collection |
Scopus |
_version_ |
1818940550555893760 |