Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic Control
Background: The enhancement in the performance of the myoelectric pattern recognition techniques based on deep learning algorithm possess computationally expensive and exhibit extensive memory behavior. Therefore, in this paper we report a deep learning framework named `Low-Complex Movement recognit...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Journal of Translational Engineering in Health and Medicine |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9197671/ |
| _version_ | 1818410619780464640 |
|---|---|
| author | Arvind Gautam Madhuri Panwar Archana Wankhede Sridhar P. Arjunan Ganesh R. Naik Amit Acharyya Dinesh K. Kumar |
| author_facet | Arvind Gautam Madhuri Panwar Archana Wankhede Sridhar P. Arjunan Ganesh R. Naik Amit Acharyya Dinesh K. Kumar |
| author_sort | Arvind Gautam |
| collection | DOAJ |
| description | Background: The enhancement in the performance of the myoelectric pattern recognition techniques based on deep learning algorithm possess computationally expensive and exhibit extensive memory behavior. Therefore, in this paper we report a deep learning framework named `Low-Complex Movement recognition-Net' (LoCoMo-Net) built with convolution neural network (CNN) for recognition of wrist and finger flexion movements; grasping and functional movements; and force pattern from single channel surface electromyography (sEMG) recording. The network consists of a two-stage pipeline: 1) input data compression; 2) data-driven weight sharing. Methods: The proposed framework was validated on two different datasets- our own dataset (DS1) and publicly available NinaPro dataset (DS2) for 16 movements and 50 movements respectively. Further, we have prototyped the proposed LoCoMo-Net on Virtex-7 Xilinx field-programmable gate array (FPGA) platform and validated for 15 movements from DS1 to demonstrate its feasibility for real-time execution. Results: The effectiveness of the proposed LoCoMo-Net was verified by a comparative analysis against the benchmarked models using the same datasets wherein our proposed model outperformed Twin- Support Vector Machine (SVM) and existing CNN based model by an average classification accuracy of 8.5 % and 16.0 % respectively. In addition, hardware complexity analysis is done to reveal the advantages of the two-stage pipeline where approximately 27 %, 49 %, 50 %, 23 %, and 43 % savings achieved in lookup tables (LUT's), registers, memory, power consumption and computational time respectively. Conclusion: The clinical significance of such sEMG based accurate and low-complex movement recognition system can be favorable for the potential improvement in quality of life of an amputated persons. |
| first_indexed | 2024-12-14T10:18:24Z |
| format | Article |
| id | doaj.art-a7ba4129913d43888ca950d834318f30 |
| institution | Directory Open Access Journal |
| issn | 2168-2372 |
| language | English |
| last_indexed | 2024-12-14T10:18:24Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Translational Engineering in Health and Medicine |
| spelling | doaj.art-a7ba4129913d43888ca950d834318f302022-12-21T23:06:43ZengIEEEIEEE Journal of Translational Engineering in Health and Medicine2168-23722020-01-01811210.1109/JTEHM.2020.30238989197671Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic ControlArvind Gautam0Madhuri Panwar1https://orcid.org/0000-0003-4763-0707Archana Wankhede2Sridhar P. Arjunan3https://orcid.org/0000-0002-7288-0380Ganesh R. Naik4https://orcid.org/0000-0003-1790-9838Amit Acharyya5https://orcid.org/0000-0002-5636-0676Dinesh K. Kumar6https://orcid.org/0000-0003-3602-4023Indian Institute of Technology Hyderabad, Hyderabad, IndiaIndian Institute of Technology Hyderabad, Hyderabad, IndiaIndian Institute of Technology Hyderabad, Hyderabad, IndiaRMIT University, Melbourne, VIC, AustraliaWestern Sydney University, Kingswood, NSW, AustraliaIndian Institute of Technology Hyderabad, Hyderabad, IndiaRMIT University, Melbourne, VIC, AustraliaBackground: The enhancement in the performance of the myoelectric pattern recognition techniques based on deep learning algorithm possess computationally expensive and exhibit extensive memory behavior. Therefore, in this paper we report a deep learning framework named `Low-Complex Movement recognition-Net' (LoCoMo-Net) built with convolution neural network (CNN) for recognition of wrist and finger flexion movements; grasping and functional movements; and force pattern from single channel surface electromyography (sEMG) recording. The network consists of a two-stage pipeline: 1) input data compression; 2) data-driven weight sharing. Methods: The proposed framework was validated on two different datasets- our own dataset (DS1) and publicly available NinaPro dataset (DS2) for 16 movements and 50 movements respectively. Further, we have prototyped the proposed LoCoMo-Net on Virtex-7 Xilinx field-programmable gate array (FPGA) platform and validated for 15 movements from DS1 to demonstrate its feasibility for real-time execution. Results: The effectiveness of the proposed LoCoMo-Net was verified by a comparative analysis against the benchmarked models using the same datasets wherein our proposed model outperformed Twin- Support Vector Machine (SVM) and existing CNN based model by an average classification accuracy of 8.5 % and 16.0 % respectively. In addition, hardware complexity analysis is done to reveal the advantages of the two-stage pipeline where approximately 27 %, 49 %, 50 %, 23 %, and 43 % savings achieved in lookup tables (LUT's), registers, memory, power consumption and computational time respectively. Conclusion: The clinical significance of such sEMG based accurate and low-complex movement recognition system can be favorable for the potential improvement in quality of life of an amputated persons.https://ieeexplore.ieee.org/document/9197671/sEMGmovement classificationsignal processingCNNdata compressionweights compression |
| spellingShingle | Arvind Gautam Madhuri Panwar Archana Wankhede Sridhar P. Arjunan Ganesh R. Naik Amit Acharyya Dinesh K. Kumar Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic Control IEEE Journal of Translational Engineering in Health and Medicine sEMG movement classification signal processing CNN data compression weights compression |
| title | Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic Control |
| title_full | Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic Control |
| title_fullStr | Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic Control |
| title_full_unstemmed | Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic Control |
| title_short | Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic Control |
| title_sort | locomo net a low complex deep learning framework for semg based hand movement recognition for prosthetic control |
| topic | sEMG movement classification signal processing CNN data compression weights compression |
| url | https://ieeexplore.ieee.org/document/9197671/ |
| work_keys_str_mv | AT arvindgautam locomonetalowcomplexdeeplearningframeworkforsemgbasedhandmovementrecognitionforprostheticcontrol AT madhuripanwar locomonetalowcomplexdeeplearningframeworkforsemgbasedhandmovementrecognitionforprostheticcontrol AT archanawankhede locomonetalowcomplexdeeplearningframeworkforsemgbasedhandmovementrecognitionforprostheticcontrol AT sridharparjunan locomonetalowcomplexdeeplearningframeworkforsemgbasedhandmovementrecognitionforprostheticcontrol AT ganeshrnaik locomonetalowcomplexdeeplearningframeworkforsemgbasedhandmovementrecognitionforprostheticcontrol AT amitacharyya locomonetalowcomplexdeeplearningframeworkforsemgbasedhandmovementrecognitionforprostheticcontrol AT dineshkkumar locomonetalowcomplexdeeplearningframeworkforsemgbasedhandmovementrecognitionforprostheticcontrol |