Finger movements recognition using minimally redundant features of wavelet denoised EMG

  • Nabasmita Phukan
  • Nayan M. KakotyEmail author
  • Prastuti Shivam
  • John Q. Gan
Original Paper


Developing prosthetic hands with high functionality and ease of use is the focus of current research in the area of Electromyogram (EMG) based prosthesis control. Although individuals with upper limb loss can perform grasping operations with currently available prosthetic hands, more intuitive control of finger movements is required to replicate the complex motor functions of human hands. A significant challenge is to classify the finger movements with higher recognition rates using a smaller number of EMG channels. This paper reports a novel criterion for selection of minimally redundant EMG feature set for classification of 10-class finger movements using two-channel EMG. The feature set is selected from wavelet denoised EMG at four decomposition levels using minimum redundancy in terms of mutual information. A set of five features: root mean square, simple square integral, slope sign change, peak frequency and power spectral ratio have been selected from 31 time and frequency domain features. Using the current state of the art classification technique based on support vector machine, we achieved 10-fold cross-validation recognition rate of 96.5 ± 0.13%. The experimental study shows that the feature set with minimum redundancy in terms of mutual information ensures the highest recognition rate with reduced computational cost.


Electromyogram Wavelet denoising Feature selection Minimum redundancy Finger movements recognition 



There is no funding source.

Compliance with Ethical Standards

Conflict of interests

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors. However, the acquisition of electromyogram using surface electrodes from four healthy subjects was in line with permission of the Institutional Ethical Committee.

Informed Consent

Informed consent was obtained from all individual participants included in the study.


  1. 1.
    Aiiboye AA, Weir RF. A heuristic fuzzy logic approach to EMG pattern recognition for multi-functional prosthetic control. IEEE Trans Neural Syst Rehabil Eng 2005;13(3):280–91.Google Scholar
  2. 2.
    Al-Timemy AH, Bugmann G, Escudero J, Outraml N. Classification of finger movements for the dexterous hand prosthesis control with surface electromyography. IEEE J Biomed Health Inf 2013;17(3):608–18.Google Scholar
  3. 3.
    Atzori M, Gijsberts A, Kuzborskij I, Elsig S, Hager AGM, Deriaz O, Castellini C, Miller H, Caputo B. Characterization of a benchmark database for myoelectric movement classification. IEEE Trans Neural Syst Rehabil Eng 2015;23(1):73–83.Google Scholar
  4. 4.
    Bennasar M, Hicks Y, Yetchi R. Feature selection using joint mutual information maximisation. Expert Syst Appl 2015;42:8520– 32.Google Scholar
  5. 5.
    Birdwell JA, Hargrove LJ, Weir RF, Kuiken TA. Extrinsic finger and thumb muscles command a virtual hand to allow individual finger and grasp control. J Biomed Signal Process Control 2015;62(1):218–26.Google Scholar
  6. 6.
    Boostani R, Moradi MH. Evaluation of the forearm EMG signal features for the control of a prosthetic hand. Physiol Meas 2003;24(2):309–19.Google Scholar
  7. 7.
    Brown G, Pocock A, Zhao MJ, Lujan M. Conditional likelihood maximisation: a unifying framework for information theoretic feature selection. Mach Learn Res 2012;13(1):27–66.MathSciNetzbMATHGoogle Scholar
  8. 8.
    Campbell C. Kernel methods: a survey of current techniques. Neurocomputing 2002;48:63–84.zbMATHGoogle Scholar
  9. 9.
    Campolo D. 2000. New developments in biomedical engineering. In-Tech, Croatoa.Google Scholar
  10. 10.
    Cipriani C, Antfolk C, Controzzi M. Online myoelectric control of a dexterous hand prosthesis by transradial amputees. IEEE Trans Neural Syst Rehab Eng 2011;19(3):260–270.Google Scholar
  11. 11.
    Crawford B, Miller K, Shenoy P, Rao R. 2005. Real-time classification of electromyographic signals for robotic control. Tech. Rep. 2005-03-05, Dept. of Computer Science University of Washington.Google Scholar
  12. 12.
    Dori P, Braiman E, Y-Tov E, Inbar GF. Classification of finger activation for use in a robotic prosthesis arm. IEEE Trans Neural Syst Rehabil Eng 2002;10(4):290–93.Google Scholar
  13. 13.
    Gailey A, Artemiadis P, Santello M. Proof of concept of an online EMG based decoding of hand postures and individual digit forces for prosthetic hand control. Front Neurol 2017;8(7):1–15.Google Scholar
  14. 14.
    Geethanjali P. Myoelectric control of prosthetic hands: state-of-the-art review. Med Dev: Evid Res 2016;9: 247–55.Google Scholar
  15. 15.
    Gijsberts A, Atzori M, Castellini C, Muller H, Caputo B. Movement error rate for evaluation of machine learning methods for sEMG-based hand movement classification. IEEE Trans Neural Syst Rehab Eng 2014; 22(4):735–44.Google Scholar
  16. 16.
    Hsu CW, Chang CC, Lin CJ. 2009. A practical guide to support vector classification. Tech rep.
  17. 17.
    Jiralerspong T, Nakanishi E, Liu C, Ishikawa J. Experimental study of real-time classification of 17 voluntary movements for multi-degree myoelectric prosthetic hand. Appl Sci 2017;7(1163):1–20.Google Scholar
  18. 18.
    Kakoty NM, Hazarika SM, Gan JQ. EMG feature set selection through linear relationship for grasp recognition. J Med Biol Eng 2016;36(6):883–90.Google Scholar
  19. 19.
    Khushaba RN, Kodagoda S, Takruri M, Dissanayake G. Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals. Expert Syst Appl 2012;39:10,731–38.Google Scholar
  20. 20.
    Krasoulis A, Kyranou I, Erden MS, Nazarpour K, Vijayakumar S. Improved prosthetic hand control with concurrent use of myoelectric and inertial measurements. J NeuroEng Rehab 2017;14(71):1–14.Google Scholar
  21. 21.
    Kwatny E, Thomas D, Kwatny H. An application of signal processing techniques to the study of myoelectric signals. IEEE Trans Biomed Eng 1970;17(4):303–13.Google Scholar
  22. 22.
    Li S, Liao J, Kwok JT. Wavelet-based feature extraction for microarray data classification. In: IEEE international conference on neural networks. Canada; 2006. p. 5028–33.Google Scholar
  23. 23.
    Liarokapis MV, Artemiadis PK, Katsiaris PT, Kyriakopoulos KJ, Manolakos ES. Learning human reach-to-grasp strategies: towards EMG-based control of robotic arm-hand systems. In: IEEE International conference on robotics and automation. Saint Paul; 2012. p. 2287–92.Google Scholar
  24. 24.
    Little MA, Varoquaux G, Saeb S, Lonini L, Jayaraman A, Mohr DC, Kording KP. Using and understanding cross-validation strategies. Perspectives on Saeb others. Gigascience 2017;6(5):1–11.Google Scholar
  25. 25.
    Mallat S. A theory for multiresolution signal decomposition - the wavelet representation. IEEE Trans Pattern Anal Mach Intell 1989;11(7):674–93.zbMATHGoogle Scholar
  26. 26.
    Oskoei MA, Hu H. Myoelectric control systems: a survey. J Biomed Signal Process Control 2007;2:275–94.Google Scholar
  27. 27.
    Paninski L. Estimation of entropy and mutual information. Neural Comput 2003;15(6):1191–253.zbMATHGoogle Scholar
  28. 28.
    Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 2005;27(8):1226–38.Google Scholar
  29. 29.
    Phinyomark A, Limsakul C, Phukpattaranont P. A novel feature extraction for robust EMG pattern recognition. J Comput 2009;1:71–80.Google Scholar
  30. 30.
    Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Experts Syst Appl 2012;39(8):7420–31.Google Scholar
  31. 31.
    Pocock A. 2017. Mitoolbox.
  32. 32.
    Qassim YT. 2014. FPGA design and implementation of wavelet coherence for EEG signals. Ph.D. thesis. Griffith University, Australia.Google Scholar
  33. 33.
    Quotb A, BBornat Y, Renaud S. Wavelet transform for real-time detection of action potentials in neural signals. Front NeuroEng 2011;4(7):1–10.Google Scholar
  34. 34.
    Reaz MBI, Hussain MS, Mohd-Yasin F. Techniques of EMG signal analysis: detection, processing, classification and applications. Biol Proc Online 2006;8(1):11–35.Google Scholar
  35. 35.
    Resnik L, Huang H, Winslow A, Crouch DL, Zhang F, Wolk N. Evaluation of EMG pattern recognition for upper limb prosthesis control: a case study in comparison with direct myoelectric control. J NeuroEng Rehab 2018;15(23):1–13.Google Scholar
  36. 36.
    Saeb S, Lonini L, Jayaraman A, Mohr DC, Kording KP. The need to approximate the use-case in clinical machine leaning. Gigascience 2017;6(5):1–9.Google Scholar
  37. 37.
    Sebelius F, Eriksson L, Balkenius C, Laurell T. Myoelectric control of a computer animated hand: a new concept based on the combined use of a tree-structured artificial neural network and a data glove. J Med Eng Technol 2006;30(1):2–10.Google Scholar
  38. 38.
    Sezgin N. A new hand fingers movements’ classification system based on bicoherence analysis of two-channels surface EMG signals. Neural Comput Appl 2017;Online First 20 November 2017:1–11.Google Scholar
  39. 39.
    Smith RJ, Tenore F, Huberdeau D, Cummings R, Thakor NV. Continuous decoding of finger position from surface EMG signals for the control of powered prostheses. In: IEEE Engineering in medicine and biology society. Canada; 2008. p. 197–200.Google Scholar
  40. 40.
    Staude G, Flachenecker C, Daumer M, Wolf W. Onset detection in surface electromyographic signals: a systematic comparison of methods. EURASIP J Adv Signal Process 2001;2001(2):67–81.zbMATHGoogle Scholar
  41. 41.
    Tenore FVG, Ramos A, Fahmy A, Acharya S, Cummings RE, Thakor NV. Decoding of individuated finger movements using surface electromyography. IEEE Trans Biomed Eng 2009;56(5):167–71.Google Scholar
  42. 42.
    Tsenov G, Zeghbib AH, Palis F, Shoylev N, Mladenov V. Neural networks for online classification of hand and finger movements using surface EMG signals. Neural Netw Appl Electr Eng 2006;8:167–71.Google Scholar
  43. 43.
    You K, Rhee K, Shin H. Finger motion decoding using EMG signals corresponding various arm postures. Exper Neurobiol 2010;19(5):54–61.Google Scholar
  44. 44.
    Zhang X, Zhou P. High-density myoelectric pattern recognition toward improved stroke rehabilitation. IEEE Trans Biomed Eng 2012;59(6):1649–57.Google Scholar

Copyright information

© IUPESM and Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Nabasmita Phukan
    • 1
  • Nayan M. Kakoty
    • 1
    Email author
  • Prastuti Shivam
    • 1
  • John Q. Gan
    • 2
  1. 1.Embedded Systems and Robotics Laboratory, School of EngineeringTezpur UniversityTezpurIndia
  2. 2.School of Computer Science and Electronic EngineeringUniversity of EssexEssexUK

Personalised recommendations