Research on Lower Limb Step Speed Recognition Method Based on Electromyography
Wearable exoskeletons play an important role in people’s lives, such as helping stroke and amputation patients to carry out rehabilitation training and so on. How to make the exoskeleton accurately judge the human action intention is the basic requirement to ensure that it can complete the correspon...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/14/3/546 |
| _version_ | 1797610100892893184 |
|---|---|
| author | Peng Zhang Pengcheng Wu Wendong Wang |
| author_facet | Peng Zhang Pengcheng Wu Wendong Wang |
| author_sort | Peng Zhang |
| collection | DOAJ |
| description | Wearable exoskeletons play an important role in people’s lives, such as helping stroke and amputation patients to carry out rehabilitation training and so on. How to make the exoskeleton accurately judge the human action intention is the basic requirement to ensure that it can complete the corresponding task. Traditional exoskeleton control signals include pressure values, joint angles and acceleration values, which can only reflect the current motion information of the human lower limbs and cannot be used to predict motion. The electromyography (EMG) signal always occurs before a certain movement; it can be used to predict the target’s gait speed and movement as the input signal. In this study, the generalization ability of a BP neural network and the timing property of a hidden Markov chain are used to properly fuse the two, and are finally used in the research of this paper. Experiments show that, using the same training samples, the recognition accuracy of the three-layer BP neural network is only 91%, while the recognition accuracy of the fusion discriminant model proposed in this paper can reach 95.1%. The results show that the fusion of BP neural network and hidden Markov chain has a strong solving ability for the task of wearable exoskeleton recognition of target step speed. |
| first_indexed | 2024-03-11T06:10:48Z |
| format | Article |
| id | doaj.art-e2620fb301174ef38ed263f2f985ddcb |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-11T06:10:48Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-e2620fb301174ef38ed263f2f985ddcb2023-11-17T12:42:20ZengMDPI AGMicromachines2072-666X2023-02-0114354610.3390/mi14030546Research on Lower Limb Step Speed Recognition Method Based on ElectromyographyPeng Zhang0Pengcheng Wu1Wendong Wang2Engineering Training Centre, Northwestern Polytechnical University, Xi’an 710000, ChinaCollege of Automation, Northwestern Polytechnical University, Xi’an 710000, ChinaCollege of Mechanical and Electrical Engineering, Northwestern Polytechnical University, Xi’an 710000, ChinaWearable exoskeletons play an important role in people’s lives, such as helping stroke and amputation patients to carry out rehabilitation training and so on. How to make the exoskeleton accurately judge the human action intention is the basic requirement to ensure that it can complete the corresponding task. Traditional exoskeleton control signals include pressure values, joint angles and acceleration values, which can only reflect the current motion information of the human lower limbs and cannot be used to predict motion. The electromyography (EMG) signal always occurs before a certain movement; it can be used to predict the target’s gait speed and movement as the input signal. In this study, the generalization ability of a BP neural network and the timing property of a hidden Markov chain are used to properly fuse the two, and are finally used in the research of this paper. Experiments show that, using the same training samples, the recognition accuracy of the three-layer BP neural network is only 91%, while the recognition accuracy of the fusion discriminant model proposed in this paper can reach 95.1%. The results show that the fusion of BP neural network and hidden Markov chain has a strong solving ability for the task of wearable exoskeleton recognition of target step speed.https://www.mdpi.com/2072-666X/14/3/546electromyography (EMG)lower limbsspeed recognition |
| spellingShingle | Peng Zhang Pengcheng Wu Wendong Wang Research on Lower Limb Step Speed Recognition Method Based on Electromyography Micromachines electromyography (EMG) lower limbs speed recognition |
| title | Research on Lower Limb Step Speed Recognition Method Based on Electromyography |
| title_full | Research on Lower Limb Step Speed Recognition Method Based on Electromyography |
| title_fullStr | Research on Lower Limb Step Speed Recognition Method Based on Electromyography |
| title_full_unstemmed | Research on Lower Limb Step Speed Recognition Method Based on Electromyography |
| title_short | Research on Lower Limb Step Speed Recognition Method Based on Electromyography |
| title_sort | research on lower limb step speed recognition method based on electromyography |
| topic | electromyography (EMG) lower limbs speed recognition |
| url | https://www.mdpi.com/2072-666X/14/3/546 |
| work_keys_str_mv | AT pengzhang researchonlowerlimbstepspeedrecognitionmethodbasedonelectromyography AT pengchengwu researchonlowerlimbstepspeedrecognitionmethodbasedonelectromyography AT wendongwang researchonlowerlimbstepspeedrecognitionmethodbasedonelectromyography |