Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of Biosignals
In the present study, we used a transformer model and a fusion of biosignals to estimate rotational acceleration in elbow and shoulder joints. To achieve our study objectives, we proposed a mechanomyography (MMG) signal isolation technique based on a variational mode decomposition (VMD) algorithm. O...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/24/6/1726 |
_version_ | 1797239394205171712 |
---|---|
author | Yu Bai Xiaorong Guan Long He Zheng Wang Zhong Li Meng Zhu |
author_facet | Yu Bai Xiaorong Guan Long He Zheng Wang Zhong Li Meng Zhu |
author_sort | Yu Bai |
collection | DOAJ |
description | In the present study, we used a transformer model and a fusion of biosignals to estimate rotational acceleration in elbow and shoulder joints. To achieve our study objectives, we proposed a mechanomyography (MMG) signal isolation technique based on a variational mode decomposition (VMD) algorithm. Our results show that the VMD algorithm delivered excellent performance in MMG signal extraction compared to the commonly used technique of empirical mode decomposition (EMD). In addition, we found that transformer models delivered estimates of joint acceleration that were more precise than those produced by mainstream time series forecasting models. The average R<sup>2</sup> values of transformer are 0.967, 0.968, and 0.935, respectively. Finally, we found that using a fusion of signals resulted in more precise estimation performance compared to using MMG signals alone. The differences between the average R<sup>2</sup> values are 0.041, 0.053, and 0.043, respectively. Taken together, the VMD isolation method, the transformer algorithm and the signal fusion technique described in this paper can be seen as supplying a robust framework for estimating rotational acceleration in upper-limb joints. Further study is warranted to examine the effectiveness of this framework in other musculoskeletal contexts. |
first_indexed | 2024-04-24T17:50:50Z |
format | Article |
id | doaj.art-a6d1eb91e40d4319b6bad8208e743a74 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-24T17:50:50Z |
publishDate | 2024-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-a6d1eb91e40d4319b6bad8208e743a742024-03-27T14:03:34ZengMDPI AGSensors1424-82202024-03-01246172610.3390/s24061726Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of BiosignalsYu Bai0Xiaorong Guan1Long He2Zheng Wang3Zhong Li4Meng Zhu5School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaIn the present study, we used a transformer model and a fusion of biosignals to estimate rotational acceleration in elbow and shoulder joints. To achieve our study objectives, we proposed a mechanomyography (MMG) signal isolation technique based on a variational mode decomposition (VMD) algorithm. Our results show that the VMD algorithm delivered excellent performance in MMG signal extraction compared to the commonly used technique of empirical mode decomposition (EMD). In addition, we found that transformer models delivered estimates of joint acceleration that were more precise than those produced by mainstream time series forecasting models. The average R<sup>2</sup> values of transformer are 0.967, 0.968, and 0.935, respectively. Finally, we found that using a fusion of signals resulted in more precise estimation performance compared to using MMG signals alone. The differences between the average R<sup>2</sup> values are 0.041, 0.053, and 0.043, respectively. Taken together, the VMD isolation method, the transformer algorithm and the signal fusion technique described in this paper can be seen as supplying a robust framework for estimating rotational acceleration in upper-limb joints. Further study is warranted to examine the effectiveness of this framework in other musculoskeletal contexts.https://www.mdpi.com/1424-8220/24/6/1726mechanomyographysurface electromyographytransformer algorithmestimation of human joint rotational acceleration |
spellingShingle | Yu Bai Xiaorong Guan Long He Zheng Wang Zhong Li Meng Zhu Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of Biosignals Sensors mechanomyography surface electromyography transformer algorithm estimation of human joint rotational acceleration |
title | Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of Biosignals |
title_full | Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of Biosignals |
title_fullStr | Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of Biosignals |
title_full_unstemmed | Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of Biosignals |
title_short | Estimating Rotational Acceleration in Shoulder and Elbow Joints Using a Transformer Algorithm and a Fusion of Biosignals |
title_sort | estimating rotational acceleration in shoulder and elbow joints using a transformer algorithm and a fusion of biosignals |
topic | mechanomyography surface electromyography transformer algorithm estimation of human joint rotational acceleration |
url | https://www.mdpi.com/1424-8220/24/6/1726 |
work_keys_str_mv | AT yubai estimatingrotationalaccelerationinshoulderandelbowjointsusingatransformeralgorithmandafusionofbiosignals AT xiaorongguan estimatingrotationalaccelerationinshoulderandelbowjointsusingatransformeralgorithmandafusionofbiosignals AT longhe estimatingrotationalaccelerationinshoulderandelbowjointsusingatransformeralgorithmandafusionofbiosignals AT zhengwang estimatingrotationalaccelerationinshoulderandelbowjointsusingatransformeralgorithmandafusionofbiosignals AT zhongli estimatingrotationalaccelerationinshoulderandelbowjointsusingatransformeralgorithmandafusionofbiosignals AT mengzhu estimatingrotationalaccelerationinshoulderandelbowjointsusingatransformeralgorithmandafusionofbiosignals |