A Study on Lower Limb Movement Intention Recognition Based on Multi-Source Information Fusion
In order to enhance the suppleness of a lower limb rehabilitation medical robot during the re-habilitation process, this study proposes a multi-source information fusion lower limb motion intention recognition method based on surface electromyographic signals (sEMG) and lower limb joint angles. To s...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10812721/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542519436869632 |
|---|---|
| author | Siyu Zong Wei Li Dawen Sun Xiaojie Wei Junjie Chen Zhengwei Yue Daxue Sun |
| author_facet | Siyu Zong Wei Li Dawen Sun Xiaojie Wei Junjie Chen Zhengwei Yue Daxue Sun |
| author_sort | Siyu Zong |
| collection | DOAJ |
| description | In order to enhance the suppleness of a lower limb rehabilitation medical robot during the re-habilitation process, this study proposes a multi-source information fusion lower limb motion intention recognition method based on surface electromyographic signals (sEMG) and lower limb joint angles. To solve the problem of data traffic surge during the collection process, a multi-source current limiting sliding time window algorithm (MLS) is proposed. The MLS algorithm controls the data flow through a flow limiting and sliding time window mechanism to ensure the efficiency and stability of the system in handling large data volumes. On this basis, the study combines the Back Propagation Generalized Algorithm Neural-network (BPGN) to construct a prediction model for lower limb joint angles. The experimental results show that under the same conditions of the algorithm, the fusion of multi-source information reduces the average error of knee joint angle prediction by 10.8° and the average error of ankle joint angle prediction by 7.2° compared with the method using a single lower limb joint angle signal. Under the same condition of input signal, the multivariate flow-limiting sliding time-window BPGN reduced the average knee joint error by 13.6° and the average ankle joint angle error by 8.5° compared to the BPGN intent recognition. The multivariate flow-limited sliding time window BPGN reduced the mean knee error by 11.2° and the mean ankle angle error by 7.4° compared to Radial Basis Function (RBF) Neural-network intent recognition. By integrating the sEMG signal and lower limb joint angle information, the system can more accurately capture the patient’s movement intention and realize more precise lower limb rehabilitation training. |
| format | Article |
| id | doaj-art-0845c5b0725843f4988aa9c97fe925f6 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-0845c5b0725843f4988aa9c97fe925f62025-01-14T00:01:06ZengIEEEIEEE Access2169-35362025-01-01135032504110.1109/ACCESS.2024.352151010812721A Study on Lower Limb Movement Intention Recognition Based on Multi-Source Information FusionSiyu Zong0https://orcid.org/0009-0004-4408-6106Wei Li1https://orcid.org/0009-0004-2119-6724Dawen Sun2https://orcid.org/0009-0005-0332-980XXiaojie Wei3https://orcid.org/0009-0008-3258-2507Junjie Chen4https://orcid.org/0009-0007-6099-339XZhengwei Yue5https://orcid.org/0009-0007-5003-6246Daxue Sun6https://orcid.org/0009-0002-5406-7561Key Laboratory of Intelligent Rehabilitation and Accessibility for People with Disabilities, Ministry of Education of China, Changchun University, Changchun, Jilin, ChinaKey Laboratory of Intelligent Rehabilitation and Accessibility for People with Disabilities, Ministry of Education of China, Changchun University, Changchun, Jilin, ChinaKey Laboratory of Intelligent Rehabilitation and Accessibility for People with Disabilities, Ministry of Education of China, Changchun University, Changchun, Jilin, ChinaKey Laboratory of Intelligent Rehabilitation and Accessibility for People with Disabilities, Ministry of Education of China, Changchun University, Changchun, Jilin, ChinaKey Laboratory of Intelligent Rehabilitation and Accessibility for People with Disabilities, Ministry of Education of China, Changchun University, Changchun, Jilin, ChinaShandong JITE Industrial Technology Company Ltd., Rizhao, Shandong, ChinaSellafield, Cumbria, U.K.In order to enhance the suppleness of a lower limb rehabilitation medical robot during the re-habilitation process, this study proposes a multi-source information fusion lower limb motion intention recognition method based on surface electromyographic signals (sEMG) and lower limb joint angles. To solve the problem of data traffic surge during the collection process, a multi-source current limiting sliding time window algorithm (MLS) is proposed. The MLS algorithm controls the data flow through a flow limiting and sliding time window mechanism to ensure the efficiency and stability of the system in handling large data volumes. On this basis, the study combines the Back Propagation Generalized Algorithm Neural-network (BPGN) to construct a prediction model for lower limb joint angles. The experimental results show that under the same conditions of the algorithm, the fusion of multi-source information reduces the average error of knee joint angle prediction by 10.8° and the average error of ankle joint angle prediction by 7.2° compared with the method using a single lower limb joint angle signal. Under the same condition of input signal, the multivariate flow-limiting sliding time-window BPGN reduced the average knee joint error by 13.6° and the average ankle joint angle error by 8.5° compared to the BPGN intent recognition. The multivariate flow-limited sliding time window BPGN reduced the mean knee error by 11.2° and the mean ankle angle error by 7.4° compared to Radial Basis Function (RBF) Neural-network intent recognition. By integrating the sEMG signal and lower limb joint angle information, the system can more accurately capture the patient’s movement intention and realize more precise lower limb rehabilitation training.https://ieeexplore.ieee.org/document/10812721/Back propagation generalized algorithm neural-networkmulti-source information fusionmulti-source current limiting sliding time window algorithmsEMG |
| spellingShingle | Siyu Zong Wei Li Dawen Sun Xiaojie Wei Junjie Chen Zhengwei Yue Daxue Sun A Study on Lower Limb Movement Intention Recognition Based on Multi-Source Information Fusion IEEE Access Back propagation generalized algorithm neural-network multi-source information fusion multi-source current limiting sliding time window algorithm sEMG |
| title | A Study on Lower Limb Movement Intention Recognition Based on Multi-Source Information Fusion |
| title_full | A Study on Lower Limb Movement Intention Recognition Based on Multi-Source Information Fusion |
| title_fullStr | A Study on Lower Limb Movement Intention Recognition Based on Multi-Source Information Fusion |
| title_full_unstemmed | A Study on Lower Limb Movement Intention Recognition Based on Multi-Source Information Fusion |
| title_short | A Study on Lower Limb Movement Intention Recognition Based on Multi-Source Information Fusion |
| title_sort | study on lower limb movement intention recognition based on multi source information fusion |
| topic | Back propagation generalized algorithm neural-network multi-source information fusion multi-source current limiting sliding time window algorithm sEMG |
| url | https://ieeexplore.ieee.org/document/10812721/ |
| work_keys_str_mv | AT siyuzong astudyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT weili astudyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT dawensun astudyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT xiaojiewei astudyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT junjiechen astudyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT zhengweiyue astudyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT daxuesun astudyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT siyuzong studyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT weili studyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT dawensun studyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT xiaojiewei studyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT junjiechen studyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT zhengweiyue studyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion AT daxuesun studyonlowerlimbmovementintentionrecognitionbasedonmultisourceinformationfusion |