Motion Pattern Recognition Based on Surface Electromyography Data and Machine Learning Classifiers: Preliminary Study
Source abstract
Abstract
Objective: The aim of this preliminary study was to recognize motion patterns by classifying time series features extracted from electromyography (EMG) data of the upper limb muscles. Methods: In this study, we tested six machine learning (ML) classification models (decision trees, support vector machines, linear discriminant, quadratic discriminant, k-nearest neighbors, and efficient logistic regression) to classify time series features segmented from processed EMG data that were acquired from eight superficial muscles of two upper limbs over performing given physical activities in two main stages (supination and neutral forearm configuration) in initial and target (isometric) positions. Results: Findings indicate that in aiming to classify stages of the upper limb with the highest performance, the following ML models should be used: (1) K-NN cityblock (F1 equals 0.973/0.992) and K-NN minkowski (0.966/0.992) for the left limb in initial or target position; (2) K-NN seuclidean (0.959/0.985) and K-NN minkowski (0.957/0.986) for the right limb in initial position; (3) K-NN cityblock (0.966/0.986), K-NN seuclidean (0.959/0.985), and K-NN minkowski (0.957/0.986) for the right limb in target position. Conclusions: Upper limb positions tested in this study can be recognized based on classification of surface EMG data by using the k-nearest neighbors models (K-NN cityblock, K-NN seuclidean or K-NN minkowski) that have to be trained separately for the right and left upper limbs.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Muscle activation and electromyography studies · Time Series Analysis and Forecasting · Sports Performance and Training
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Mechanics and Machine Design, Faculty of Mechanical Engineering and Ship Technology, Gdansk University of Technology, Str. G. Narutowicza 11/12, 80-233 Gdansk, Poland
Funding
Ministry of National Education Poland
References (57)
Show source-provided references
1. The use of wearable sensors for the classification of electromyographic signal patterns based on changes in the elbow joint angle10.1016/j.procs.2021.05.043 ↗
2. EMG physical action detection using recurrence plot approach10.1016/j.procs.2024.04.145 ↗
3. A channel-fused gated temporal convolutional network for EMG-based gesture recognition10.1016/j.bspc.2024.106408 ↗
4. XAI for myo-controlled prosthesis: Explaining EMG data for hand gesture classification10.1016/j.knosys.2021.108053 ↗
5. A testing system for a real-time gesture classification using surface, E.M.G
6. Improving robotic hand control via adaptive fuzzy-PI controller using classification of EMG signals10.1016/j.heliyon.2022.e11931 ↗
7. Kocejko, T., Rumiński, J., Przystup, P., Poliński, A., and Wtorek, J. (2017, January 17–19). The role of EMG module in hybrid interface of prosthetic arm. Proceedings of the 2017 10th International Conference on Human System Interactions (HSI), Ulsan, Republic of Korea.10.1109/HSI.2017.8004992 ↗
8. Event driven sliding mode control of a lower limb exoskeleton based on a continuous neural network electromyographic signal classifier10.1016/j.mechatronics.2020.102451 ↗
9. Deep learning approach to improve the recognition of hand gesture with multi force variation using electromyography signal from amputees10.1016/j.medengphy.2024.104131 ↗
10. Towards integration of domain knowledge-guided feature engineering and deep feature learning in surface electromyography-based hand movement recognition10.1155/2021/4454648 ↗
11. Tortora, S., Tonin, L., Chisari, C., Micera, S., Menegatti, E., and Artoni, F. (2020). Hybrid human–machine interface for gait decoding through Bayesian fusion of EEG and EMG classifiers. Front. Neurorobot., 14.10.3389/fnbot.2020.582728 ↗
12. Feature and muscle selection for an effective hand motion classifier based on electromyography
13. Limb position tolerant pattern recognition for myoelectric prosthesis control with adaptive sparse representations from extreme learning10.1109/TBME.2017.2719400 ↗
14. Machine learning-based novel approach to classify the shoulder motion of upper limb amputees10.1016/j.bbe.2019.07.007 ↗
15. A machine learning strategy for locomotion classification and parameter estimation using fusion of wearable sensors10.1109/TBME.2021.3065809 ↗
16. A decision-based velocity ramp for minimizing the effect of misclassifications during real-time pattern recognition control10.1109/TBME.2011.2155063 ↗
17. The effects of electrode size and orientation on the sensitivity of myoelectric pattern recognition systems to electrode shift10.1109/TBME.2011.2159216 ↗
18. Improving myoelectric pattern recognition robustness to electrode shift by changing interelectrode distance and electrode configuration10.1109/TBME.2011.2177662 ↗
19. Surface electromyography based explainable artificial intelligence fusion framework for feature selection of hand gesture recognition10.1016/j.engappai.2024.109119 ↗
20. Joint kinematics, kinetics and muscle synergy patterns during transitions between locomotion modes10.1109/TBME.2022.3208381 ↗
21. Real-time hand gesture recognition by decoding motor unit discharges across multiple motor tasks from surface electromyography10.1109/TBME.2023.3234642 ↗
22. sEMG-based gesture recognition using temporal history10.1109/TBME.2023.3261336 ↗
23. Deep learning and machine learning techniques to improve hand movement classification in myoelectric control system10.1016/j.bbe.2021.03.006 ↗
24. Hand movement recognition from sEMG signals using Fourier decomposition method10.1016/j.bbe.2021.03.004 ↗
25. On EMG based dexterous robotic telemanipulation: Assessing machine learning techniques, feature extraction methods, and shared control schemes10.1109/ACCESS.2022.3206436 ↗
26. Muscle Synergy Analysis for Stroke During Two Degrees of Freedom Reaching Task on Horizontal Plane10.1007/s12541-019-00251-5 ↗
27. Comparison of machine learning methods in sEMG signal processing for shoulder motion recognition10.1016/j.bspc.2021.102577 ↗
28. Using machine learning algorithms for grasp strength recognition in rehabilitation planning10.1016/j.rineng.2023.101660 ↗
29. Comparison of KNN and random forest algorithms in classifying EMG signals
30. Hu, Y., Wong, Y., Wei, W., Du, Y., Kankanhalli, M., and Geng, W. (2018). A novel attention-based hybrid CNN–RNN architecture for sEMG-based gesture recognition. PLoS ONE, 13.10.1371/journal.pone.0206049 ↗
31. EMGHandNet: A hybrid CNN and BI-LSTM architecture for hand activity classification using surface EMG signals10.1016/j.bbe.2022.02.005 ↗
32. Tryon, J., and Trejos, A. (2021). Evaluating convolutional neural networks as a method of EEG–EMG fusion. Front. Neurorobot., 15.10.3389/fnbot.2021.692183 ↗
33. Graph Regularization Methods in Soft Detector Fusion10.1109/ACCESS.2023.3344776 ↗
34. Hand gesture recognition using smooth wavelet packet transformation and hybrid CNN based on surface EMG and accelerometer signal10.1016/j.bspc.2023.105141 ↗
35. Deep back propagation–long short-term memory network based upper-limb sEMG signal classification for automated rehabilitation10.1016/j.bbe.2020.05.003 ↗
36. Classification of simultaneous movements using surface EMG pattern recognition10.1109/TBME.2012.2232293 ↗
37. Classification of upper limb phantom movements in transhumeral amputees using electromyographic and kinematic features10.1016/j.engappai.2017.10.017 ↗
38. Analysis of dynamics of EMG signal variations in fatiguing contractions of muscles using transition network approach10.1109/TIM.2021.3063777 ↗
39. Diagnosis of neuromuscular disorders using DT-CWT and rotation forest ensemble classifier10.1109/TIM.2019.2918596 ↗
40. Detecting Muscle Fatigue among Community-Dwelling Senior Adults with Shape Features of the Probability Density Function of sEMG10.1186/s12984-024-01497-5 ↗
41. Safont, G., Salazar, A., Vergara, L., and Rodríguez, A. (2013, January 5–7). New Applications of Sequential ICA Mixtures Models Compared with Dynamic Bayesian Networks for EEG Signal Processing. Proceedings of the 2013 Fifth International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN), Madrid, Spain.10.1109/CICSYN.2013.29 ↗
42. Real-time embedded EMG signal analysis for wrist–hand pose identification10.1109/TSP.2020.2985299 ↗
43. A novel event-driven spiking convolutional neural network for electromyography pattern recognition10.1109/TBME.2023.3258606 ↗
44. Single channel EMG-based continuous terrain identification with simple classifier for lower limb prosthesis10.1016/j.bbe.2019.07.002 ↗
45. Characterization of muscle fatigue in the lower limb by sEMG and angular position using the WFD protocol10.1016/j.bbe.2021.06.003 ↗
46. A bionic hand controlled by hand gesture recognition based on surface EMG signals: A preliminary study10.1016/j.bbe.2017.11.001 ↗
47. Exploring the relationship between EMG feature space characteristics and control performance in machine learning myoelectric control10.1109/TNSRE.2020.3029873 ↗
48. Barbero, M., Merletti, R., and Rainoldi, A. (2012). Atlas of Muscle Innervation Zones: Understanding Surface Electromyography and Its Applications, Springer.10.1007/978-88-470-2463-2 ↗
49. Towards hand grip force assessment by using EMG estimators10.1016/j.measurement.2024.114137 ↗
50. Classification assessment methods10.1016/j.aci.2018.08.003 ↗
51. EMAHA-DB1: A new upper limb sEMG dataset for classification of activities of daily living10.1109/TIM.2023.3279873 ↗
52. Neuromuscular disorders detection through time–frequency analysis and classification of multi-muscular EMG signals using Hilbert–Huang transform10.1016/j.bspc.2021.103037 ↗
53. Real-time classification of EMG Myo armband data using support vector machine10.1016/j.irbm.2022.06.001 ↗
54. Artificial intelligence-based classification of motor unit action potentials in real-world needle EMG recordings10.1016/j.clinph.2023.10.008 ↗
55. Empowering human–robot interaction using sEMG sensor: Hybrid deep learning model for accurate hand gesture recognition10.1016/j.rineng.2023.101639 ↗
56. Hand gesture classification using time–frequency images and transfer learning based on CNN10.1016/j.bspc.2022.103787 ↗
57. Wojnicz, W., Sobierajska-Rek, A., Zagrodny, B., Ludwicki, M., Jabłońska-Brudło, J., and Forysiak, K. (2022). A new approach to assess quality of motion in functional task of upper limb in Duchenne muscular dystrophy. Appl. Sci., 12.10.3390/app122312247 ↗