A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable Sensors

<b>Background</b>: In the fields of rehabilitation, public health, military training and other domains, the accurate and effective monitoring of exercise intensity during exercise can control the occurrence of sports injuries, which is of great significance for people’s healthy lives. &l...

Full description

Saved in:
Bibliographic Details
Main Authors: Lei Pang, Yi Li, Ming-Xia Liao, Jia-Gang Qiu, Hui Li, Zhen Wang, Gang Sun
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3437
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331072431554560
author Lei Pang
Yi Li
Ming-Xia Liao
Jia-Gang Qiu
Hui Li
Zhen Wang
Gang Sun
author_facet Lei Pang
Yi Li
Ming-Xia Liao
Jia-Gang Qiu
Hui Li
Zhen Wang
Gang Sun
author_sort Lei Pang
collection DOAJ
description <b>Background</b>: In the fields of rehabilitation, public health, military training and other domains, the accurate and effective monitoring of exercise intensity during exercise can control the occurrence of sports injuries, which is of great significance for people’s healthy lives. <b>Objective</b>: This study combined easily collectable multi-dimensional sensor data and various algorithm models to achieve cross-individual recognition of low, middle and high levels of exercise intensity. <b>Methods</b>: This study compared the recognition performance of different algorithm models using acceleration and angular velocity sensors worn on seven body parts through individualised body data characteristics. <b>Results</b>: The recognition performances of two classical machine learning algorithms were the worst, with a recognition rate of only 82.97% and 80.31%. The performances of two ensemble learning algorithms were slightly better, with a recognition rate of 88.86% and 87.35%. The deep sub-domain adaptation network algorithm proposed in this study exhibited the best performance, with a recognition rate of 92.87%. This study utilised multi-dimensional sensors to construct a cross-individual exercise intensity recognition model for different parts of the body, and the overall recognition rate of the left part was higher than that of the right part. Moreover, the recognition effect upon wearing sensors on the left side of the body is better than the right in running events. <b>Conclusions</b>: The results of this study have demonstrated the effectiveness of combining domain adaptation methods and multi-dimensional sensors for cross-individual exercise intensity recognition, laying a solid theoretical foundation for broader-scale cross-individual exercise intensity recognition in future research.
format Article
id doaj-art-2b67a71479424f3994e6eaa089214bec
institution Kabale University
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-2b67a71479424f3994e6eaa089214bec2025-08-20T03:46:45ZengMDPI AGSensors1424-82202025-05-012511343710.3390/s25113437A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable SensorsLei Pang0Yi Li1Ming-Xia Liao2Jia-Gang Qiu3Hui Li4Zhen Wang5Gang Sun6Institute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, Beijing 100091, ChinaInstitute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, Beijing 100091, ChinaInstitute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, Beijing 100091, ChinaSchool of Information and Control Engineering, Southwest University of Science and Technology, Mianyang 621010, ChinaInstitute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, Beijing 100091, ChinaInstitute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, Beijing 100091, ChinaInstitute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, Beijing 100091, China<b>Background</b>: In the fields of rehabilitation, public health, military training and other domains, the accurate and effective monitoring of exercise intensity during exercise can control the occurrence of sports injuries, which is of great significance for people’s healthy lives. <b>Objective</b>: This study combined easily collectable multi-dimensional sensor data and various algorithm models to achieve cross-individual recognition of low, middle and high levels of exercise intensity. <b>Methods</b>: This study compared the recognition performance of different algorithm models using acceleration and angular velocity sensors worn on seven body parts through individualised body data characteristics. <b>Results</b>: The recognition performances of two classical machine learning algorithms were the worst, with a recognition rate of only 82.97% and 80.31%. The performances of two ensemble learning algorithms were slightly better, with a recognition rate of 88.86% and 87.35%. The deep sub-domain adaptation network algorithm proposed in this study exhibited the best performance, with a recognition rate of 92.87%. This study utilised multi-dimensional sensors to construct a cross-individual exercise intensity recognition model for different parts of the body, and the overall recognition rate of the left part was higher than that of the right part. Moreover, the recognition effect upon wearing sensors on the left side of the body is better than the right in running events. <b>Conclusions</b>: The results of this study have demonstrated the effectiveness of combining domain adaptation methods and multi-dimensional sensors for cross-individual exercise intensity recognition, laying a solid theoretical foundation for broader-scale cross-individual exercise intensity recognition in future research.https://www.mdpi.com/1424-8220/25/11/3437cross-individualexercise intensityensemble learningdomain adaptationdeep subdomain adaptation network
spellingShingle Lei Pang
Yi Li
Ming-Xia Liao
Jia-Gang Qiu
Hui Li
Zhen Wang
Gang Sun
A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable Sensors
Sensors
cross-individual
exercise intensity
ensemble learning
domain adaptation
deep subdomain adaptation network
title A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable Sensors
title_full A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable Sensors
title_fullStr A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable Sensors
title_full_unstemmed A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable Sensors
title_short A Feasibility Study of Domain Adaptation for Exercise Intensity Recognition Based on Wearable Sensors
title_sort feasibility study of domain adaptation for exercise intensity recognition based on wearable sensors
topic cross-individual
exercise intensity
ensemble learning
domain adaptation
deep subdomain adaptation network
url https://www.mdpi.com/1424-8220/25/11/3437
work_keys_str_mv AT leipang afeasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT yili afeasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT mingxialiao afeasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT jiagangqiu afeasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT huili afeasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT zhenwang afeasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT gangsun afeasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT leipang feasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT yili feasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT mingxialiao feasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT jiagangqiu feasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT huili feasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT zhenwang feasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors
AT gangsun feasibilitystudyofdomainadaptationforexerciseintensityrecognitionbasedonwearablesensors