Vol. 28 No. 3 (2025) Cover Image
Vol. 28 No. 3 (2025)

Published: September 30, 2025

Pages: 461-468

Articles

Performance Evaluation of Gesture Recognition Using Myo Armband and Gyroscope Sensors

S. M. Sarhan 1 M. Z. Al-Faiz 2 A. M. Takhakh 3
1 Dep. of Biomedical Eng., College of Engineering, University of Warith Al-Anbiyaa, Karbala, Iraq
2 Dep. of Control and Computer, College of Information Engineering, Al-Nahrain University, Baghdad-Iraq
3 Dep. of Mechanical Eng., College of Engineering, Al-Nahrain University, Baghdad-Iraq
History
  • Received: May 11, 2024
  • Revised: July 12, 2024
  • Accepted: March 12, 2025
  • Available Online: September 29, 2025
DOI

https://doi.org/10.29194/NJES.28030461

Abstract

The technique of recording muscle signals is crucial in determining how effectively they can be utilized for individual benefit. This study focuses on hand movements recognized by using the Myo armband and Motion Processing Unit (MPU) 6050 sensors. Linear Discriminant Analysis (LDA), K-nearest neighbors (k-NN), and Support Vector Machine (SVM) were employed for classification. sEMG signals using the Myo armband for 7 hand gestures and 2 elbow movements were recorded from 10 healthy subjects. Results showed that SVM outperforms LDA and k-NN in accuracy in both cases, the sensor is worn once on the arm and again on the forearm. regions. The window size and choice of features significantly influence system accuracy, with SVM achieving an average accuracy of 89.84%. Besides that, the fusion of Myo Armband sensor and gyroscope sensor through OR rule makes significant enhancement in recognition accuracy with which is reached to 97.0135%. In conclusion, the Myo armband, when worn on the forearm, proves practical for hand gesture recognition, with SVM offering superior recognition accuracy. Furthermore, the combination of the Myo Armband sensor and the gyroscope sensor showed higher recognition accuracy.

Keywords

References

  1. A. Hogenhuis, “Social network engagement during human-robot interaction,” in Companion of the 2023 ACM/IEEE Int. Conf. on Human-Robot Interaction, Mar. 2023. DOI:10.1145/3568294.3579976
  2. S. Hall and J. Stephens, Anatomy and Physiology. Amsterdam: Elsevier, 2019.
  3. S. Madarshahian and M. L. Latash, “Effects of hand muscle function and dominance on intra-muscle synergies,” Hum. Mov. Sci., vol. 82, p. 102936, Apr. 2022. DOI:10.1016/j.humov.2022.102936
  4. S. Bisi, L. De Luca, B. Shrestha, Z. Yang, and V. Gandhi, “Development of an EMG-controlled mobile robot,” Robotics, vol. 7, no. 3, p. 36, 2018. DOI:10.3390/robotics7030036
  5. A. Sharma, I. Sharma, and A. Kumar, “Signal acquisition and time–frequency perspective of EMG signal-based systems and applications,” IETE Tech. Rev., vol. 41, no. 4, pp. 466–485, Oct. 2023. DOI:10.1080/02564602.2023.2265897
  6. M. A. Ozdemir, D. H. Kisa, O. Guren, and A. Akan, “Dataset for multi-channel surface electromyography (SEMG) signals of hand gestures,” Data Brief, vol. 41, p. 107921, Apr. 2022. DOI:10.1016/j.dib.2022.107921
  7. Y. Long, Z. Du, W. Wang, and W. Dong, “Development of a wearable exoskeleton rehabilitation system based on hybrid control mode,” Int. J. Adv. Robot. Syst., vol. 13, no. 5, p. 172988141666484, Sep. 2016. DOI:10.1177/1729881416664847
  8. E. L. Ting, A. Chai, and L. P. Chin, “A review on EMG signal classification and applications,” Int. J. Signal Process. Syst., vol. 9, no. 1, pp. 1–6, Mar. 2022. DOI:10.18178/ijsps.10.1.1-6
  9. S. S. Bangaru, C. Wang, and F. Aghazadeh, “Data quality and reliability assessment of wearable EMG and IMU sensor for construction activity recognition,” Sensors, vol. 20, no. 18, p. 5264, Sep. 2020. DOI:10.3390/s20185264
  10. T. S. Chu, A. Y. Chua, and E. L. Secco, “A wearable myo gesture armband controlling Sphero BB-8 robot,” HighTech Innov. J., vol. 1, no. 4, pp. 179–186, 2020. DOI:10.28991/HIJ-2020-01-04-05
  11. P. Visconti, F. Gaetani, G. A. Zappatore, and P. Primiceri, "Technical features and functionalities of myo armband: An overview on related literature and advanced applications of myoelectric armbands mainly focused on arm prostheses," Int. J. Smart Sens. Intell. Syst., vol. 11, no. 1, pp. 1-25, 2018. DOI:10.21307/ijssis-2018-005
  12. G. Dougherty, Pattern Recognition and Classification: An Introduction. New York, NY: Springer, 2013. DOI:10.1007/978-1-4614-5323-9
  13. H. F. Hassan, S. J. Abou-Loukh, and I. K. Ibraheem, “Teleoperated robotic arm movement using electromyography signal with wearable myo armband,” J. King Saud Univ. Eng. Sci., vol. 32, no. 6, pp. 378–387, 2020. DOI:10.1016/j.jksues.2019.05.001
  14. H. R. Mahmood, M. K. Hussein, and R. A. Abedraba, “Development of low-cost biosignal acquisition system for ECG, EMG, and EOG,” Wasit J. Eng. Sci., vol. 10, no. 3, pp. 191–202, Dec. 2022. DOI:10.31185/ejuow.vol10.iss3.352
  15. A. Ahmed, Y. Al Mashhadany, R. Ahmad, and F. Khaleefah, “Smart prosthetics controller types: Review,” Anbar J. Eng. Sci., vol. 15, no. 2, pp. 131–154, Dec. 2024. DOI:10.37649/aengs.2024.152744.1097
  16. I. L. Salim, A. S. Jalal, and O. A. Awad, “A dataset for emotion recognition for Iraqi autism individuals as a step towards EEG-based therapeutic intervention,” Iraqi J. Inf. Commun. Technol., vol. 7, no. 3, pp. 55–70, Dec. 2024. DOI:10.31987/ijict.7.3.284
  17. M. Z. Al-Faiz and Z. J. Ali, “Humanoid robotic hand (HRH) based on EMG signal for amputees persons,” Int. J. Emerg. Trends Eng. Res., vol. 6, no. 4, pp. 19–26, 2018. DOI:10.30534/ijeter/2018/02642018
  18. Y. Narayan, “HB VSEMG signal classification with time domain and frequency domain features using LDA and ANN classifier,” Mater. Today Proc., vol. 37, pp. 3226–3230, 2021. DOI:10.1016/j.matpr.2020.09.091
  19. A. Furui, “Evaluating classifier confidence for surface EMG pattern recognition,” in Proc. 45th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), Jul. 2023. DOI:10.1109/EMBC40787.2023.10340977
  20. E. Ozturk Kiyak, B. Ghasemkhani, and D. Birant, “High-level K-nearest neighbors (HLKNN): A supervised machine learning model for classification analysis,” Electronics, vol. 12, no. 18, p. 3828, Sep. 2023. DOI:10.3390/electronics12183828