Computational analysis of each model.
<div><p>This study aims to develop a cost-effective and reliable motion monitoring device capable of comprehensive fatigue analysis. It achieves this objective by integrating surface electromyography (sEMG) and accelerometer (ACC) signals through a feature fusion strategy. The study intr...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , |
| Published: |
2024
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852025440461389824 |
|---|---|
| author | Dinghong Mu (14204200) |
| author2 | Jian Wang (5901) Fenglei Li (1940623) Wujin Hu (20108297) Rong Chen (29176) |
| author2_role | author author author author |
| author_facet | Dinghong Mu (14204200) Jian Wang (5901) Fenglei Li (1940623) Wujin Hu (20108297) Rong Chen (29176) |
| author_role | author |
| dc.creator.none.fl_str_mv | Dinghong Mu (14204200) Jian Wang (5901) Fenglei Li (1940623) Wujin Hu (20108297) Rong Chen (29176) |
| dc.date.none.fl_str_mv | 2024-11-04T18:36:13Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0310035.t004 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/Computational_analysis_of_each_model_/27608447 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Science Policy Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified three fatigue states scale attention mechanism proposed optimization algorithm preprocessing phase involves multilevel attention mechanism level attention mechanisms level attention mechanism integrating surface electromyography improving feature extraction feature fusion strategy computational analysis indicates comprehensive fatigue analysis cnn &# 8217 dimensional fused data model &# 8217 52 %, 92 92 %, 92 handling data 38 %, 30 %, 13 %, xlink "> testing times study introduces study aims neuron levels minimal impact cnns ). amplitude envelope ablation experiments |
| dc.title.none.fl_str_mv | Computational analysis of each model. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>This study aims to develop a cost-effective and reliable motion monitoring device capable of comprehensive fatigue analysis. It achieves this objective by integrating surface electromyography (sEMG) and accelerometer (ACC) signals through a feature fusion strategy. The study introduces a multi-level attention mechanism for classification, leveraging convolutional neural networks (CNNs). The preprocessing phase involves a local feature attention mechanism that enhances local waveform features using the amplitude envelope. A dual-scale attention mechanism, operating at both channel and neuron levels, is employed to enhance the model’s learning from high-dimensional fused data, improving feature extraction and generalization. The local feature attention mechanism significantly improves the model’s classification accuracy and convergence, as demonstrated in ablation experiments. The model, optimized with multi-level attention mechanisms, excels in accuracy and generalization, particularly in handling data with pseudo-artifacts. Computational analysis indicates that the proposed optimization algorithm has minimal impact on CNN’s training and testing times. The study achieves recognition accuracies of 92.52%, 92.38%, and 92.30%, as well as F1-scores of 91.92%, 92.13%, and 92.29% for the three fatigue states, affirming its reliability. This research provides technical support for the development of affordable and dependable wearable motion monitoring devices.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_9d8941feaf7fbd2dd8d3ac3bbad4def3 |
| identifier_str_mv | 10.1371/journal.pone.0310035.t004 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/27608447 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Computational analysis of each model.Dinghong Mu (14204200)Jian Wang (5901)Fenglei Li (1940623)Wujin Hu (20108297)Rong Chen (29176)Science PolicySpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedthree fatigue statesscale attention mechanismproposed optimization algorithmpreprocessing phase involvesmultilevel attention mechanismlevel attention mechanismslevel attention mechanismintegrating surface electromyographyimproving feature extractionfeature fusion strategycomputational analysis indicatescomprehensive fatigue analysiscnn &# 8217dimensional fused datamodel &# 821752 %, 9292 %, 92handling data38 %,30 %,13 %,xlink ">testing timesstudy introducesstudy aimsneuron levelsminimal impactcnns ).amplitude envelopeablation experiments<div><p>This study aims to develop a cost-effective and reliable motion monitoring device capable of comprehensive fatigue analysis. It achieves this objective by integrating surface electromyography (sEMG) and accelerometer (ACC) signals through a feature fusion strategy. The study introduces a multi-level attention mechanism for classification, leveraging convolutional neural networks (CNNs). The preprocessing phase involves a local feature attention mechanism that enhances local waveform features using the amplitude envelope. A dual-scale attention mechanism, operating at both channel and neuron levels, is employed to enhance the model’s learning from high-dimensional fused data, improving feature extraction and generalization. The local feature attention mechanism significantly improves the model’s classification accuracy and convergence, as demonstrated in ablation experiments. The model, optimized with multi-level attention mechanisms, excels in accuracy and generalization, particularly in handling data with pseudo-artifacts. Computational analysis indicates that the proposed optimization algorithm has minimal impact on CNN’s training and testing times. The study achieves recognition accuracies of 92.52%, 92.38%, and 92.30%, as well as F1-scores of 91.92%, 92.13%, and 92.29% for the three fatigue states, affirming its reliability. This research provides technical support for the development of affordable and dependable wearable motion monitoring devices.</p></div>2024-11-04T18:36:13ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0310035.t004https://figshare.com/articles/dataset/Computational_analysis_of_each_model_/27608447CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/276084472024-11-04T18:36:13Z |
| spellingShingle | Computational analysis of each model. Dinghong Mu (14204200) Science Policy Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified three fatigue states scale attention mechanism proposed optimization algorithm preprocessing phase involves multilevel attention mechanism level attention mechanisms level attention mechanism integrating surface electromyography improving feature extraction feature fusion strategy computational analysis indicates comprehensive fatigue analysis cnn &# 8217 dimensional fused data model &# 8217 52 %, 92 92 %, 92 handling data 38 %, 30 %, 13 %, xlink "> testing times study introduces study aims neuron levels minimal impact cnns ). amplitude envelope ablation experiments |
| status_str | publishedVersion |
| title | Computational analysis of each model. |
| title_full | Computational analysis of each model. |
| title_fullStr | Computational analysis of each model. |
| title_full_unstemmed | Computational analysis of each model. |
| title_short | Computational analysis of each model. |
| title_sort | Computational analysis of each model. |
| topic | Science Policy Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified three fatigue states scale attention mechanism proposed optimization algorithm preprocessing phase involves multilevel attention mechanism level attention mechanisms level attention mechanism integrating surface electromyography improving feature extraction feature fusion strategy computational analysis indicates comprehensive fatigue analysis cnn &# 8217 dimensional fused data model &# 8217 52 %, 92 92 %, 92 handling data 38 %, 30 %, 13 %, xlink "> testing times study introduces study aims neuron levels minimal impact cnns ). amplitude envelope ablation experiments |