Analysis of electrode locations on limb condition effect for myoelectric pattern recognition.
Electrode placement
Limb conditions
Myoelectric signals
Pattern recognition
Robustness
Journal
Journal of neuroengineering and rehabilitation
ISSN: 1743-0003
Titre abrégé: J Neuroeng Rehabil
Pays: England
ID NLM: 101232233
Informations de publication
Date de publication:
03 Oct 2024
03 Oct 2024
Historique:
received:
08
03
2024
accepted:
06
09
2024
medline:
4
10
2024
pubmed:
4
10
2024
entrez:
3
10
2024
Statut:
epublish
Résumé
Gesture recognition using surface electromyography (sEMG) has garnered significant attention due to its potential for intuitive and natural control in wearable human-machine interfaces. However, ensuring robustness remains essential and is currently the primary challenge for practical applications. This study investigates the impact of limb conditions and analyzes the influence of electrode placement. Both static and dynamic limb conditions were examined using electrodes positioned on the wrist, elbow, and the midpoint between them. Initially, we compared classification performance across various training conditions at these three electrode locations. Subsequently, a feature space analysis was conducted to quantify the effects of limb conditions. Finally, strategies for group training and feature selection were explored to mitigate these effects. The results indicate that with the state-of-the-art method, classification performance at the wrist was comparable to that at the middle position, both of which outperformed the elbow, consistent with the findings from the feature space analysis. In inter-condition classification, training under dynamic limb conditions yielded better results than training under static conditions, especially at the positions covered by dynamic training. Additionally, fast and slow movement speeds produced similar performance outcomes. To mitigate the effects of limb conditions, adding more training conditions reduced classification errors; however, this reduction plateaued after four conditions, resulting in classification errors of 22.72%, 22.65%, and 26.58% for the wrist, middle, and elbow, respectively. Feature selection further improved classification performance, reducing errors to 19.98%, 19.75%, and 27.14% at the respective electrode locations, using three optimal features derived from single-condition training. The study demonstrated that the impact of limb conditions was mitigated when electrodes were placed near the wrist. Dynamic limb condition training, combined with feature optimization, proved to be an effective strategy for reducing this effect. This work contributes to enhancing the robustness of myoelectric-controlled interfaces, thereby advancing the development of wearable intelligent devices.
Sections du résumé
BACKGROUND
BACKGROUND
Gesture recognition using surface electromyography (sEMG) has garnered significant attention due to its potential for intuitive and natural control in wearable human-machine interfaces. However, ensuring robustness remains essential and is currently the primary challenge for practical applications.
METHODS
METHODS
This study investigates the impact of limb conditions and analyzes the influence of electrode placement. Both static and dynamic limb conditions were examined using electrodes positioned on the wrist, elbow, and the midpoint between them. Initially, we compared classification performance across various training conditions at these three electrode locations. Subsequently, a feature space analysis was conducted to quantify the effects of limb conditions. Finally, strategies for group training and feature selection were explored to mitigate these effects.
RESULTS
RESULTS
The results indicate that with the state-of-the-art method, classification performance at the wrist was comparable to that at the middle position, both of which outperformed the elbow, consistent with the findings from the feature space analysis. In inter-condition classification, training under dynamic limb conditions yielded better results than training under static conditions, especially at the positions covered by dynamic training. Additionally, fast and slow movement speeds produced similar performance outcomes. To mitigate the effects of limb conditions, adding more training conditions reduced classification errors; however, this reduction plateaued after four conditions, resulting in classification errors of 22.72%, 22.65%, and 26.58% for the wrist, middle, and elbow, respectively. Feature selection further improved classification performance, reducing errors to 19.98%, 19.75%, and 27.14% at the respective electrode locations, using three optimal features derived from single-condition training.
CONCLUSIONS
CONCLUSIONS
The study demonstrated that the impact of limb conditions was mitigated when electrodes were placed near the wrist. Dynamic limb condition training, combined with feature optimization, proved to be an effective strategy for reducing this effect. This work contributes to enhancing the robustness of myoelectric-controlled interfaces, thereby advancing the development of wearable intelligent devices.
Identifiants
pubmed: 39363228
doi: 10.1186/s12984-024-01466-y
pii: 10.1186/s12984-024-01466-y
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
177Informations de copyright
© 2024. The Author(s).
Références
Jiang N, Chen C, He J, Meng J, Pan L, Su S, et al. Bio-robotics research for non-invasive myoelectric neural interfaces for upper-limb prosthetic control: a 10-year perspective review. Natl Sci Rev. 2023;10(5):nwad048.
doi: 10.1093/nsr/nwad048
pubmed: 37056442
pmcid: 10089583
Farina D, Jiang N, Rehbaum H, Holobar A, Graimann B, Dietl H, et al. The extraction of neural information from the surface EMG for the control of upper-limb prostheses: emerging avenues and challenges. IEEE Trans Neural Syst Rehabil Eng. 2014;22(4):797–809.
doi: 10.1109/TNSRE.2014.2305111
pubmed: 24760934
Roche AD, Rehbaum H, Farina D, Aszmann OC. Prosthetic myoelectric control strategies: a clinical perspective. Curr Surg Rep. 2014. https://doi.org/10.1007/s40137-013-0044-8 .
doi: 10.1007/s40137-013-0044-8
He J, Zhang D, Jiang N, Sheng X, Farina D, Zhu X. User adaptation in long-term, open-loop myoelectric training: implications for EMG pattern recognition in prosthesis control. J Neural Eng. 2015;12(4):046005.
doi: 10.1088/1741-2560/12/4/046005
pubmed: 26028132
Fougner A, Scheme E, Chan ADC, Englehart K, Stavdahl O. Resolving the limb position effect in myoelectric pattern recognition. IEEE Trans Neural Syst Rehabil Eng. 2011;19(6):644–51.
doi: 10.1109/TNSRE.2011.2163529
pubmed: 21846608
Geng YJ, Zhou P, Li GL. Toward attenuating the impact of arm positions on electromyography pattern-recognition based motion classification in transradial amputees. J Neuroeng Rehabil. 2012. https://doi.org/10.1186/1743-0003-9-74 .
doi: 10.1186/1743-0003-9-74
pubmed: 23036049
pmcid: 3551659
Liu J, Zhang D, Sheng X, Zhu X. Quantification and solutions of arm movements effect on sEMG pattern recognition. Biomed Signal Proces. 2014;13:189–97.
doi: 10.1016/j.bspc.2014.05.001
He J, Niu X, Zhao P, Lin C, Jiang N. From forearm to wrist: deep learning for surface electromyography-based gesture recognition. IEEE Trans Neural Syst Rehabil Eng. 2023. https://doi.org/10.1109/TNSRE.2023.3341220 .
doi: 10.1109/TNSRE.2023.3341220
pubmed: 38032786
Botros FS, Phinyomark A, Scheme EJ. Electromyography-based gesture recognition: is it time to change focus from the forearm to the wrist? Ieee T Ind Inform. 2022;18(1):174–84.
doi: 10.1109/TII.2020.3041618
Islam MJ, Ahmad S, Ferdousi A, Haque F, Reaz MBI, Bhuiyan MAS, et al. Optimizing electrode positions on forearm to increase SNR and myoelectric pattern recognition performance. Eng Appl Artif Intel. 2023;122:106160.
doi: 10.1016/j.engappai.2023.106160
Pan TY, Tsai WL, Chang CY, Yeh CW, Hu MC. A hierarchical hand gesture recognition framework for sports referee training-based EMG and accelerometer sensors. Ieee T Cybernetics. 2022;52(5):3172–83.
doi: 10.1109/TCYB.2020.3007173
Vásconez JP, López LIB, Caraguay ALV, Cruz PJ, Alvarez R, Benalcázar ME. A hand gesture recognition system using emg and reinforcement learning: a Q-learning approach. In: Farkaš I, Masulli P, Otte S, Wermter S, editors. Artificial neural networks and machine learning - Icann 2021, Pt Iv. Cham: Springer International Publishing; 2021. p. 580–91.
doi: 10.1007/978-3-030-86380-7_47
Yamanoi Y, Ogiri Y, Kato R. EMG-based posture classification using a convolutional neural network for a myoelectric hand. Biomed Signal Process. 2020;55:101574.
doi: 10.1016/j.bspc.2019.101574
Scheme EJ, Englehart KB, Hudgins BS. Selective classification for improved robustness of myoelectric control under nonideal conditions. IEEE Trans Biomed Eng. 2011;58(6):1698–705.
doi: 10.1109/TBME.2011.2113182
pubmed: 21317073
Kawaguchi J, Yoshimoto S, Kuroda Y, Oshiro O. Estimation of finger joint angles based on electromechanical sensing of wrist shape. IEEE Trans Neural Syst Rehabil Eng. 2017;25(9):1409–18.
doi: 10.1109/TNSRE.2016.2626800
pubmed: 27845665
Xiloyannis M, Gavriel C, Thomik AAC, Faisal AA. Gaussian process autoregression for simultaneous proportional multi-modal prosthetic control with natural hand kinematics. IEEE Trans Neural Syst Rehabil Eng. 2017;25(10):1785–801.
doi: 10.1109/TNSRE.2017.2699598
pubmed: 28880183
Ngeo JG, Tamei T, Shibata T. Continuous and simultaneous estimation of finger kinematics using inputs from an EMG-to-muscle activation model. J Neuroeng Rehabil. 2014. https://doi.org/10.1186/1743-0003-11-122 .
doi: 10.1186/1743-0003-11-122
pubmed: 25123024
pmcid: 4148535
Wang H, Tao Q, Zhang X. Ensemble learning method for the continuous decoding of hand joint angles. Sensors. 2024;24(2):660.
doi: 10.3390/s24020660
Wen Y, Kim SJ, Avrillon S, Levine JT, Hug F, Pons JL. A deep CNN framework for neural drive estimation from HD-EMG across contraction intensities and joint angles. IEEE Trans Neural Syst Rehabil Eng. 2022;30:2950–9.
doi: 10.1109/TNSRE.2022.3215246
pubmed: 36251912
Hai W, Qing T, Na S, Xiaodong Z. Simultaneous estimation of hand joints’ angles toward sEMG-driven human-robot interaction. Ieee Access. 2022;10:109385–94.
doi: 10.1109/ACCESS.2022.3212046
Ameri A, Akhaee MA, Scheme E, Englehart K. A deep transfer learning approach to reducing the effect of electrode shift in EMG pattern recognition-based control. IEEE Trans Neural Syst Rehabil Eng. 2020;28(2):370–9.
doi: 10.1109/TNSRE.2019.2962189
pubmed: 31880557
Bao TZ, Zaidi SAR, Xie SQ, Yang PF, Zhang ZQ. A CNN-LSTM hybrid model for wrist kinematics estimation using surface electromyography. IEEE Trans Instrum Meas. 2021;70:1.
Montazerin M, Rahimian E, Naderkhani F, Atashzar SF, Yanushkevich S, Mohammadi A. Transformer-based hand gesture recognition from instantaneous to fused neural decomposition of high-density EMG signals. Sci Rep. 2023. https://doi.org/10.1038/s41598-023-36490-w .
doi: 10.1038/s41598-023-36490-w
pubmed: 37419881
pmcid: 10329032
Fang YF, Yang JN, Zhou DL, Ju ZJ. Modelling EMG driven wrist movements using a bio-inspired neural network. Neurocomputing. 2022;470:89–98.
doi: 10.1016/j.neucom.2021.10.104
Hudgins B, Parker P, Scott RN. A new strategy for multifunction myoelectric control. IEEE Trans Biomed Eng. 1993;40(1):82–94.
doi: 10.1109/10.204774
pubmed: 8468080
Bunderson NE, Kuiken TA. Quantification of feature space changes with experience during electromyogram pattern recognition control. IEEE Trans Neural Syst Rehabil Eng. 2012;20(3):239–46.
doi: 10.1109/TNSRE.2011.2182525
pubmed: 22262686
Cote-Allard U, Fall CL, Drouin A, Campeau-Lecours A, Gosselin C, Glette K, et al. Deep learning for electromyographic hand gesture signal classification using transfer learning. IEEE Trans Neural Syst Rehabil Eng. 2019;27(4):760–71.
doi: 10.1109/TNSRE.2019.2896269
pubmed: 30714928
Qi JX, Jiang GZ, Li GF, Sun Y, Tao B. Surface EMG hand gesture recognition system based on PCA and GRNN. Neural Comput Appl. 2020;32(10):6343–51.
doi: 10.1007/s00521-019-04142-8