Optimal strategy of sEMG feature and measurement position for grasp force estimation.
Grasp force estimation based on surface electromyography (sEMG) is essential for the dexterous control of a prosthetic hand. Nowadays, although increasing the number of sEMG measurement positions and extracting more features are common methods to increase the accuracy of grasp force estimation, it w...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0247883 |
| _version_ | 1819032146552029184 |
|---|---|
| author | Changcheng Wu Qingqing Cao Fei Fei Dehua Yang Baoguo Xu Guanglie Zhang Hong Zeng Aiguo Song |
| author_facet | Changcheng Wu Qingqing Cao Fei Fei Dehua Yang Baoguo Xu Guanglie Zhang Hong Zeng Aiguo Song |
| author_sort | Changcheng Wu |
| collection | DOAJ |
| description | Grasp force estimation based on surface electromyography (sEMG) is essential for the dexterous control of a prosthetic hand. Nowadays, although increasing the number of sEMG measurement positions and extracting more features are common methods to increase the accuracy of grasp force estimation, it will increase the computational burden. In this paper, an approach based on analysis of variance (ANOVA) and generalized regression neural network (GRNN) for optimal measurement positions and features is proposed, with the purpose of using fewer measurement positions or features to achieve higher estimation accuracy. Firstly, we captured six channels of sEMG from subjects' forearm and grasp force synchronously. Then, four kinds of features in time domain are extracted from each channel of sEMG. By combining different measurement position sets (MPSs) and feature set (FSs), we construct 945 data sets. These data sets are fed to GRNN to realize grasp force estimation. Normalized root mean square error (NRMS), normalized mean of absolute error (NMAE), and correlation coefficient (CC) between estimated grasp force and actual force are introduced to evaluate the performance of grasp force estimation. Finally, ANOVA and Tukey HSD testing are introduced to analyze grasp force estimation results so as to obtain the optimal measurement positions and features. We obtain the optimal MPSs for grasp force estimation when different FSs are employed, and the optimal FSs when different MPSs are utilized. |
| first_indexed | 2024-12-21T06:57:18Z |
| format | Article |
| id | doaj.art-9bb598fc00284fd8b4801d1a65b1e819 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-21T06:57:18Z |
| publishDate | 2021-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-9bb598fc00284fd8b4801d1a65b1e8192022-12-21T19:12:19ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-01163e024788310.1371/journal.pone.0247883Optimal strategy of sEMG feature and measurement position for grasp force estimation.Changcheng WuQingqing CaoFei FeiDehua YangBaoguo XuGuanglie ZhangHong ZengAiguo SongGrasp force estimation based on surface electromyography (sEMG) is essential for the dexterous control of a prosthetic hand. Nowadays, although increasing the number of sEMG measurement positions and extracting more features are common methods to increase the accuracy of grasp force estimation, it will increase the computational burden. In this paper, an approach based on analysis of variance (ANOVA) and generalized regression neural network (GRNN) for optimal measurement positions and features is proposed, with the purpose of using fewer measurement positions or features to achieve higher estimation accuracy. Firstly, we captured six channels of sEMG from subjects' forearm and grasp force synchronously. Then, four kinds of features in time domain are extracted from each channel of sEMG. By combining different measurement position sets (MPSs) and feature set (FSs), we construct 945 data sets. These data sets are fed to GRNN to realize grasp force estimation. Normalized root mean square error (NRMS), normalized mean of absolute error (NMAE), and correlation coefficient (CC) between estimated grasp force and actual force are introduced to evaluate the performance of grasp force estimation. Finally, ANOVA and Tukey HSD testing are introduced to analyze grasp force estimation results so as to obtain the optimal measurement positions and features. We obtain the optimal MPSs for grasp force estimation when different FSs are employed, and the optimal FSs when different MPSs are utilized.https://doi.org/10.1371/journal.pone.0247883 |
| spellingShingle | Changcheng Wu Qingqing Cao Fei Fei Dehua Yang Baoguo Xu Guanglie Zhang Hong Zeng Aiguo Song Optimal strategy of sEMG feature and measurement position for grasp force estimation. PLoS ONE |
| title | Optimal strategy of sEMG feature and measurement position for grasp force estimation. |
| title_full | Optimal strategy of sEMG feature and measurement position for grasp force estimation. |
| title_fullStr | Optimal strategy of sEMG feature and measurement position for grasp force estimation. |
| title_full_unstemmed | Optimal strategy of sEMG feature and measurement position for grasp force estimation. |
| title_short | Optimal strategy of sEMG feature and measurement position for grasp force estimation. |
| title_sort | optimal strategy of semg feature and measurement position for grasp force estimation |
| url | https://doi.org/10.1371/journal.pone.0247883 |
| work_keys_str_mv | AT changchengwu optimalstrategyofsemgfeatureandmeasurementpositionforgraspforceestimation AT qingqingcao optimalstrategyofsemgfeatureandmeasurementpositionforgraspforceestimation AT feifei optimalstrategyofsemgfeatureandmeasurementpositionforgraspforceestimation AT dehuayang optimalstrategyofsemgfeatureandmeasurementpositionforgraspforceestimation AT baoguoxu optimalstrategyofsemgfeatureandmeasurementpositionforgraspforceestimation AT guangliezhang optimalstrategyofsemgfeatureandmeasurementpositionforgraspforceestimation AT hongzeng optimalstrategyofsemgfeatureandmeasurementpositionforgraspforceestimation AT aiguosong optimalstrategyofsemgfeatureandmeasurementpositionforgraspforceestimation |