Advertisement

Exploring the Relation Between EMG Pattern Recognition and Sampling Rate Using Spectrogram

  • Jingwei Too
  • Abdul Rahim AbdullahEmail author
  • Norhashimah Mohd Saad
  • Nursabillilah Mohd Ali
  • Tengku Nor Shuhada Tengku Zawawi
Original Article
  • 1 Downloads

Abstract

The application of electromyography (EMG) has shown great success in rehabilitation engineering. With the existing multiple-channel EMG recording system, the detection and classification of EMG pattern have become viable. The purpose of this study is to investigate the relation between sampling rate and EMG pattern recognition by using spectrogram. The features are extracted from spectrogram coefficients and the principal component analysis is applied for dimensionality reduction. In addition, the optimal Hanning window size is identified and selected before performance evaluation. For noise evaluation, the additive white Gaussian noise (AGWN) is added to the EMG signal at 30, 25, 20 dB SNR. The results illustrated that the 512 Hz sampling rate can maintain a small decrement of 0.76% accuracy compared to 1024 Hz. However, when the AGWN is added, the 256 and 512 Hz sampling rates showed a greater reduction in overall classification performance. For a lower SNR, the gaps in classification accuracy between 1024 Hz, 512 Hz and 256 Hz sampling rates are obviously presented. It signifies that reducing the sampling rate lower than 1024 Hz might not be a good choice since the noise and artifact have to be taken into consideration in a real system.

Keywords

Electromyography Sampling rate Spectrogram K-nearest neighbor Support vector machines 

Notes

Acknowledgements

This work was supported by Skim Zamalah UTeM and Ministry of Higher Education Malaysia under Grant FRGS/1/2017/TK04/FKE-CeRIA/F00334.

References

  1. 1.
    Subasi A, Kiymik MK (2010) Muscle fatigue detection in EMG using time–frequency methods, ICA and neural networks. J Med Syst 34(4):777–785CrossRefGoogle Scholar
  2. 2.
    Alkan A, Günay M (2012) Identification of EMG signals using discriminant analysis and SVM classifier. Expert Syst Appl 39(1):44–47CrossRefGoogle Scholar
  3. 3.
    Sahu G et al (2015) “HHT based features for discrimination of EMG signals”, in information systems design and intelligent applications. Springer, New Delhi, pp 95–103CrossRefGoogle Scholar
  4. 4.
    Chen H et al (2017) Exploring the relation between EMG sampling frequency and hand motion recognition accuracy. In: Proceeding of IEEE international conference, CanadaGoogle Scholar
  5. 5.
    Subasi A (2013) Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput Biol Med 43(5):576–586CrossRefGoogle Scholar
  6. 6.
    Li G et al (2010) Selection of sampling rate for EMG pattern recognition based prosthesis control. In: Proceeding of IEEE engineering in medicine and biology, ArgentinaGoogle Scholar
  7. 7.
    Smith LH et al (2011) Determining the optimal window length for pattern recognition-based myoelectric control: balancing the competing effects of classification error and controller delay. IEEE Trans Neural Syst Rehabil Eng 19(2):186–192CrossRefGoogle Scholar
  8. 8.
    Al-Timemy AH et al (2013) Classification of finger movements for the dexterous hand prosthesis control with surface electromyography. IEEE J Biomed Health Inform 17(3):608–618CrossRefGoogle Scholar
  9. 9.
    De Luca CJ et al (2010) Filtering the surface EMG signal: movement artifact and baseline noise contamination. J Biomech 43(8):1573–1579CrossRefGoogle Scholar
  10. 10.
    Chowdhury RH et al (2013) Surface electromyography signal processing and classification techniques. Sensors 13(9):12431–12466CrossRefGoogle Scholar
  11. 11.
    Joshi D et al (2015) High energy spectrogram with integrated prior knowledge for EMG-based locomotion classification. Med Eng Phys 37(5):518–524CrossRefGoogle Scholar
  12. 12.
    Li X et al (2014) Power spectral analysis of surface electromyography (EMG) at matched contraction levels of the first dorsal interosseous muscle in stroke survivors. Clin Neurophysiol 125(5):988–994CrossRefGoogle Scholar
  13. 13.
    Zhang X, Zhou P (2013) Filtering of surface EMG using ensemble empirical mode decomposition. Med Eng Phys 35(4):537–542CrossRefGoogle Scholar
  14. 14.
    Phinyomark A et al (2012) Feature extraction and reduction of wavelet transform coefficients for EMG pattern classification. Elektron Ir Elektrotech 122(6):27–32CrossRefGoogle Scholar
  15. 15.
    Kim KS et al (2011) Comparison of k-nearest neighbor, quadratic discriminant and linear discriminant analysis in classification of electromyogram signals based on the wrist-motion directions. Curr Appl Phys 11(3):740–745CrossRefGoogle Scholar
  16. 16.
    Geethanjali P, Ray KK (2011) Identification of motion from multi-channel EMG signals for control of prosthetic hand. Australas Phys Eng Sci Med 34(3):419–427CrossRefGoogle Scholar
  17. 17.
    Gokgoz E, Subasi A (2014) Effect of multiscale PCA de-noising on EMG signal classification for diagnosis of neuromuscular disorders. J Med Syst 38(4):31CrossRefGoogle Scholar
  18. 18.
    Gokgoz E, Subasi A (2015) Comparison of decision tree algorithms for EMG signal classification using DWT. Biomed Signal Process Control 18:138–144CrossRefGoogle Scholar
  19. 19.
    Stegeman DF, Hermens HJ (2007) Standards for surface electromyography: the European project (SENIAM). Enschede Roessingh Research and Development, pp 108–112Google Scholar
  20. 20.
    Khokhar ZO et al (2010) Surface EMG pattern recognition for real-time control of a wrist exoskeleton. Biomed Eng Online 9:41CrossRefGoogle Scholar
  21. 21.
  22. 22.
    Phinyomark A et al (2013) EMG feature evaluation for improving myoelectric pattern recognition robustness. Expert Syst Appl 40(12):4832–4840CrossRefGoogle Scholar
  23. 23.
    Young AJ et al (2013) Classification of simultaneous movements using surface EMG pattern recognition. IEEE Trans Biomed Eng 60(5):1250–1258CrossRefGoogle Scholar
  24. 24.
    Hamedi M et al (2015) Facial neuromuscular signal classification by means of least square support vector machine for MuCI. Appl Soft Comput 30:83–93CrossRefGoogle Scholar
  25. 25.
    Roux JL et al (2010) Fast signal reconstruction from magnitude stft spectrogram based on spectrogram consistency. In: Proceeding of digital audio effects DAFx’10Google Scholar
  26. 26.
    Zhang K et al (2015) The detection of crackles based on mathematical morphology in spectrogram analysis. Technol Health Care 23(s2):S489–S494CrossRefGoogle Scholar
  27. 27.
    Shair EF et al (2016) Auto-segmentation analysis of EMG signal for lifting muscle contraction activities. J Telecommun Electron Comput Eng JTEC 8(7):17–22Google Scholar
  28. 28.
    Subasi A, Ismail Gursoy M (2010) EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst Appl 37(12):8659–8666CrossRefGoogle Scholar
  29. 29.
    Riillo F et al (2014) Optimization of EMG-based hand gesture recognition: supervised vs. unsupervised data preprocessing on healthy subjects and transradial amputees. Biomed Signal Process Control 14:117–125CrossRefGoogle Scholar
  30. 30.
    Zhang X, Zhou P (2012) High-density myoelectric pattern recognition toward improved stroke rehabilitation. IEEE Trans Biomed Eng 59(6):1649–1657CrossRefGoogle Scholar

Copyright information

© The Korean Institute of Electrical Engineers 2019

Authors and Affiliations

  • Jingwei Too
    • 1
  • Abdul Rahim Abdullah
    • 1
    Email author
  • Norhashimah Mohd Saad
    • 2
  • Nursabillilah Mohd Ali
    • 1
  • Tengku Nor Shuhada Tengku Zawawi
    • 1
  1. 1.Fakulti Kejuruteraan ElektrikUniversiti Teknikal Malaysia MelakaDurian TunggalMalaysia
  2. 2.Fakulti Kejuruteraan Elektronik dan Kejuruteraan KomputerUniversiti Teknikal Malaysia MelakaDurian TunggalMalaysia

Personalised recommendations