Application of electromyography (EMG) and electrical impedance myography (EIM) in controlling a bionic hand prosthesis: A comparison of efficiency and precision EMG and EIM in algorithms for controlling bionic prostheses

• Autorzy: Peła Agnieszka

Identyfikatory

DOI

10.5604/01.3001.0054.9270

• Języki publikacji: EN

Abstrakty

EN

Aim: The study aimed to develop an innovative algorithm for controlling a bionic hand prosthesis based on simultaneous analysis of electromyography (EMG) and electrical impedance myography (EIM) signals using continuous wavelet transform (CWT). The efficiency of both methods in motion classification was analyzed and compared, and the impact of electrode placement on classification accuracy was evaluated. Methods: The BIOPAC MP36R system was employed to acquire EMG and EIM signals during six predefined hand movements from two distinct electrode placements. A total of 600 measurements were collected for each type of signal. Data were subjected to preliminary, time-domain, frequency-domain, and time-frequency analyses to extract key features for each movement. The developed classification algorithm utilized a k-nearest neighbors (k-NN) approach based on extracted signal features. The algorithm was trained on data obtained during the first measurement session and validated on an independent dataset. Results: The results demonstrated that EIM signals outperformed EMG in motion classification accuracy, allowing for the differentiation of flexion and extension at the preliminary analysis stage. EIM achieved 100% accuracy in 9 out of 12 analyzed cases, with a minimum accuracy of 84%. In contrast, EMG signals enabled only basic movement detection without distinguishing between flexion and extension during the preliminary analysis phase. Electrode placement significantly affected classification performance, with differences exceeding 82% depending on placement. Conclusions: The findings indicate the considerable advantage of EIM over traditional EMG in controlling bionic hand prostheses, opening new possibilities for more precise and intuitive control. The study also highlights the importance of optimal electrode placement to enhance the functionality of future bionic prostheses.

Słowa kluczowe

EN

electromyography; EMG; electrical impedance myography; EIM; prosthesis control; motion recognition algorithms; bionic prostheses; biological signals

• Wydawca: Uniwersytet Jagielloński - Collegium Medicum ; Index Copernicus Sp. z o.o.
• Czasopismo: Bio-Algorithms and Med-Systems
• Rocznik: 2024
• Tom: Vol. 20, no. 1
• Strony: 135--145
• Opis fizyczny: Bibliogr. 17 poz., rys., tab.

Twórcy

autor

Peła Agnieszka

• Department of Biomedical Engineering, Koszalin University of Technology; Śniadeckich Street 2, 75-452 Koszalin, Poland

• https://orcid.org/0009-0005-2462-9406

Bibliografia

• 1. Wheeler KR, Chang MH, Knuth KH. Gesture-based control and EMG decomposition. IEEE Trans Syst Man Cybern. 2016;4:503-14.
• 2. Glowinski S, Pecolt S, Błażejewski A, Młyński B. Control of Brushless Direct-Current Motors Using Bioelectric EMG Signals. Sensors (Basel). 2022 Sep 9;22(18):6829.
• 3. Pylatiuk C, Schulz S, Dudenhausen H. Comparison of surface EMG monitoring electrodes for long-term use in rehabilitation device control. In: Conference Proceedings of the IEEE International Conference on Rehabilitation Robotics (ICORR 2009); 2009 June 23-26; Kyoto, Japan. New Jersey: IEEE; 2009. p. 300-4.
• 4. Kusche R, Ryschka M. Combining bioimpedance and EMG measurements for reliable muscle contraction detection. IEEE Sens J. 2019;19(15):11687-96.
• 5. Grimnes S, Martinsen OG. Bioimpedance and Bioelectricity Basics. 3rd ed. Academic Press: New York; 2014.
• 6. Paszkiel S, Sikora M. Recognition of finger movement based on electromyogram analysis. Pomiary Autom Robot. 2018;22:11-6.
• 7. Akhmadeev K, Mikhaylov A, Ivanov A. A testing system for real-time gesture classification using surface EMG. IFAC-PapersOnLine. 2017;50:11498-503.
• 8. Ajiboye AB, Wei RF. A heuristic fuzzy logic approach to EMG pattern recognition for multifunctional prosthesis control. IEEE Trans Neural Syst Rehabil Eng. 2005;13:280-91.
• 9. Shi M, Li H, Zhao J, Li M-Q, Wang L, Xie N-G. EEG signal classification based on SVM with improved squirrel search algorithm. Biomed Eng Biomed Tech. 2021;66:137-52.
• 10. George FP, Sharma V, Kumar A. Recognition of emotional states using EEG signals based on time-frequency analysis and SVM classifier. Int J Electr Comput Eng. 2019;9:1012-20.
• 11. Behera S, Mohanty MN. Classification of EEG Signal Using SVM. In: Pradhan G, Morris S, Nayak N, editors. Advances in Electrical Control and Signal Systems. Singapore; Springer; 2020. p. 859-69.
• 12. Rutkove SB. Electrical impedance myography: Background, current state, and future directions. Muscle Nerve. 2009;40:936-46.
• 13. Kobelev A, Shchukin S. Anthropomorphic prosthesis control based on the electrical impedance signals analysis. In: 2018 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT). IEEE; 2018 7-8 May; Yekaterinburg, Russia. New Jersey, USA: IEEE; 2018. p. 33-6.
• 14. Kalevo L, Lehmussola A, Pelkonen P, Kainulainen S, Korkalainen H, Myllymaa K. Effect of sweating on electrode-skin contact impedances and artifacts in EEG recordings with various screen-printed Ag/AgCl electrodes. IEEE Access. 2020;8:50934-43.
• 15. Cho Y, Kim P. Electrical impedance myography (EIM) for multi-class prosthetic robot hand control. In: 2020 20th International Conference on Control, Automation and Systems (ICCAS); 2020 Oct 13-16; Seoul, Korea. New Jersey, USA: IEEE; 2020. p. 1092-4.
• 16. Sanchez B, Rutkove SB. Present uses, future applications, and technical underpinnings of electrical impedance myography. Curr Neurol Neurosci Rep. 2017;17:86.
• 17. Rutkove SB, Lee KS, Shiffman CA, Aaron R. Electrical impedance myography as a biomarker to assess ALS progression. Amyotroph Lateral Scler. 2012;13:439-45.