sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning
Conventional classification of hand motions and continuous joint angle estimation based on sEMG have been widely studied in recent years. The classification task focuses on discrete motion recognition and shows poor real-time performance, while continuous joint angle estimation evaluates the real-ti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9949 |
| _version_ | 1797455341679542272 |
|---|---|
| author | Kaikui Zheng Shuai Liu Jinxing Yang Metwalli Al-Selwi Jun Li |
| author_facet | Kaikui Zheng Shuai Liu Jinxing Yang Metwalli Al-Selwi Jun Li |
| author_sort | Kaikui Zheng |
| collection | DOAJ |
| description | Conventional classification of hand motions and continuous joint angle estimation based on sEMG have been widely studied in recent years. The classification task focuses on discrete motion recognition and shows poor real-time performance, while continuous joint angle estimation evaluates the real-time joint angles by the continuity of the limb. Few researchers have investigated continuous hand action prediction based on hand motion continuity. In our study, we propose the key state transition as a condition for continuous hand action prediction and simulate the prediction process using a sliding window with long-term memory. Firstly, the key state modeled by GMM-HMMs is set as the condition. Then, the sliding window is used to dynamically look for the key state transition. The prediction results are given while finding the key state transition. To extend continuous multigesture action prediction, we use model pruning to improve reusability. Eight subjects participated in the experiment, and the results show that the average accuracy of continuous two-hand actions is 97% with a 70 ms time delay, which is better than LSTM (94.15%, 308 ms) and GRU (93.83%, 300 ms). In supplementary experiments with continuous four-hand actions, over 85% prediction accuracy is achieved with an average time delay of 90 ms. |
| first_indexed | 2024-03-09T15:52:01Z |
| format | Article |
| id | doaj.art-e3d0ce1002604e199c34d63155e2d488 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:52:01Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e3d0ce1002604e199c34d63155e2d4882023-11-24T17:58:01ZengMDPI AGSensors1424-82202022-12-012224994910.3390/s22249949sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model PruningKaikui Zheng0Shuai Liu1Jinxing Yang2Metwalli Al-Selwi3Jun Li4School of Advanced Manufacturing, Fuzhou University, Quanzhou 362200, ChinaSchool of Advanced Manufacturing, Fuzhou University, Quanzhou 362200, ChinaQuanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou 362216, ChinaQuanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou 362216, ChinaQuanzhou Institute of Equipment Manufacturing, Chinese Academy of Sciences, Quanzhou 362216, ChinaConventional classification of hand motions and continuous joint angle estimation based on sEMG have been widely studied in recent years. The classification task focuses on discrete motion recognition and shows poor real-time performance, while continuous joint angle estimation evaluates the real-time joint angles by the continuity of the limb. Few researchers have investigated continuous hand action prediction based on hand motion continuity. In our study, we propose the key state transition as a condition for continuous hand action prediction and simulate the prediction process using a sliding window with long-term memory. Firstly, the key state modeled by GMM-HMMs is set as the condition. Then, the sliding window is used to dynamically look for the key state transition. The prediction results are given while finding the key state transition. To extend continuous multigesture action prediction, we use model pruning to improve reusability. Eight subjects participated in the experiment, and the results show that the average accuracy of continuous two-hand actions is 97% with a 70 ms time delay, which is better than LSTM (94.15%, 308 ms) and GRU (93.83%, 300 ms). In supplementary experiments with continuous four-hand actions, over 85% prediction accuracy is achieved with an average time delay of 90 ms.https://www.mdpi.com/1424-8220/22/24/9949sEMGGMM-HMMskey state transitionmodel pruningcontinuous two-hand action predictionsliding window |
| spellingShingle | Kaikui Zheng Shuai Liu Jinxing Yang Metwalli Al-Selwi Jun Li sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning Sensors sEMG GMM-HMMs key state transition model pruning continuous two-hand action prediction sliding window |
| title | sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning |
| title_full | sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning |
| title_fullStr | sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning |
| title_full_unstemmed | sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning |
| title_short | sEMG-Based Continuous Hand Action Prediction by Using Key State Transition and Model Pruning |
| title_sort | semg based continuous hand action prediction by using key state transition and model pruning |
| topic | sEMG GMM-HMMs key state transition model pruning continuous two-hand action prediction sliding window |
| url | https://www.mdpi.com/1424-8220/22/24/9949 |
| work_keys_str_mv | AT kaikuizheng semgbasedcontinuoushandactionpredictionbyusingkeystatetransitionandmodelpruning AT shuailiu semgbasedcontinuoushandactionpredictionbyusingkeystatetransitionandmodelpruning AT jinxingyang semgbasedcontinuoushandactionpredictionbyusingkeystatetransitionandmodelpruning AT metwallialselwi semgbasedcontinuoushandactionpredictionbyusingkeystatetransitionandmodelpruning AT junli semgbasedcontinuoushandactionpredictionbyusingkeystatetransitionandmodelpruning |