Advertisement

A novel feature extraction method for machine learning based on surface electromyography from healthy brain

  • Gongfa LiEmail author
  • Jiahan Li
  • Zhaojie Ju
  • Ying Sun
  • Jianyi Kong
Original Article
  • 13 Downloads

Abstract

Feature extraction is one of most important steps in the control of multifunctional prosthesis based on surface electromyography (sEMG) pattern recognition. In this paper, a new sEMG feature extraction method based on muscle active region is proposed. This paper designs an experiment to classify four hand motions using different features. This experiment is used to prove that new features have better classification performance. The experimental results show that the new feature, active muscle regions (AMR), has better classification performance than other traditional features, mean absolute value (MAV), waveform length (WL), zero crossing (ZC) and slope sign changes (SSC). The average classification errors of AMR, MAV, WL, ZC and SSC are 13%, 19%, 26%, 24% and 22%, respectively. The new EMG features are based on the mapping relationship between hand movements and forearm active muscle regions. This mapping relationship has been confirmed in medicine. We obtain the active muscle regions data from the original EMG signal by the new feature extraction algorithm. The results obtained from this algorithm can well represent hand motions. On the other hand, the new feature vector size is much smaller than other features. The new feature can narrow the computational cost. This proves that the AMR can improve sEMG pattern recognition accuracy rate.

Keywords

sEMG New feature Active muscle regions Machine learning 

Notes

Acknowledgements

This work was supported by grants of Natural Science Foundation of China (Grant Nos. 51575407, 51575338, 51575412, 61733011), Grants of National Natural Science Foundation of China (Grant Nos. 51505349, 51575407, 51575338, 51575412, 61733011) and the Grants of National Defense Pre-Research Foundation of Wuhan University of Science and Technology (GF201705). This paper is funded by Wuhan University of Science and Technology graduate students short-term study abroad special funds.

Compliance with ethical standards

Conflicts of interest

The authors declare no conflict of interest.

References

  1. 1.
    Yinfeng F, Hettiarachchi N, Dalin Z, Honghai L (2015) Multi-modal sensing techniques for interfacing hand prostheses: a review. IEEE Sens J 15:6065–6076Google Scholar
  2. 2.
    Castellini C, Smagt P (2009) Surface EMG in advanced hand prosthetics. Biol Cybern 100:35–47Google Scholar
  3. 3.
    Wentao C, Wentao S, Gongfa L, Guozhang J, Honghai L (2018) Jointly network: a network based on CNN and RBM for gesture recognition. Neural Comput Appl.  https://doi.org/10.1007/s00521-018-3775-8 Google Scholar
  4. 4.
    Arieta A, Yokoi H, Arai T, Yu W (2006) Study on the effects of electrical stimulation on the pattern recognition for an EMG prosthetic application. In: Proc IEEE Int Conf Eng Med Biol Soc, pp 6919–6922Google Scholar
  5. 5.
    Zhang D, Chen X, Li S, Hu P, Zhu X (2011) EMG controlled multifunctional prosthetic hand: preliminary clinical study and experimental demonstration. In: Proc IEEE Int Conf Robot Autom, pp 4670–4675Google Scholar
  6. 6.
    Yang H, Gongfa L, Yajie L, Ying S, Jianyi K, Guozhang J, Du J (2017) Gesture recognition based on an improved local sparse representation classification algorithm. Clust Comput.  https://doi.org/10.1007/s10586-017-1237-1 Google Scholar
  7. 7.
    Bei L, Ying S, Gongfa L, Jianyi K, Guozhang J, Du J, Honghai L (2017) Gesture recognition based on modified adaptive orthogonal matching pursuit algorithm. Clust Comput.  https://doi.org/10.1007/s10586-017-1231-7 Google Scholar
  8. 8.
    Wei M, Gongfa L, Guozhang J, Yinfeng F, Zhaojie J, Honghai L (2015) Optimal grasp planning of multi-fingered robotic hands: a review. Appl Comput Math 14(3):238–247MathSciNetzbMATHGoogle Scholar
  9. 9.
    Gongfa L, Heng T, Ying S, Jianyi K, Guozhang J (2017) Hand gesture recognition based on convolution neural network. Clust Comput.  https://doi.org/10.1007/s10586-017-1435-x Google Scholar
  10. 10.
    Du J, Zujia Z, Gongfa L, Ying S, Jianyi K, Guozhang J, Hegen X, Bo T, Shuang X, Hui Y, Honghai L, Zhaojie J (2018) Gesture recognition based on binocular vision. Clust Comput.  https://doi.org/10.1007/s10586-018-1844-5 Google Scholar
  11. 11.
    Ying S, Cuiqiao L, Gongfa L, Guozhang J, Du J, Honghai L, Zhigao Z, Wanneng S (2018) Gesture recognition based on kinect and sEMG signal fusion. Mob Netw Appl. 23(4):797–805Google Scholar
  12. 12.
    Weiliang D, Gongfa L, Guozhang J, Yinfeng F, Zhaojie J, Honghai L (2015) Intelligent computation in grasping control of dexterous robot hand. J Comput Theor Nanosci 12(12):6096–6099Google Scholar
  13. 13.
    Zhe L, Gongfa L, Guozhang J, Yinfeng F, Zhaojie J, Honghai L (2015) Intelligent Computation of grasping and manipulation for multi-fingered robotic hands. J Comput Theor Nanosci 12(12):6192–6197Google Scholar
  14. 14.
    Scott R (1966) Myoelectric control of prostheses. Arch Phys Med Rehabil 47:174Google Scholar
  15. 15.
    Zhang F, Li P, Hou Z (2012) sEMG-based continuous estimation of joint angles of human legs by using BP neural network. Neurocomputing 78:139–148Google Scholar
  16. 16.
    Jiang D, Gongfa L, Ying S, Jianyi K, Bo T (2018) Gesture recognition based on skeletonization algorithm and CNN with ASL database. Multimedia Tools Appl.  https://doi.org/10.1007/s11042-018-6748-0 Google Scholar
  17. 17.
    Lee J, Kim M, Kim K (2015) A robust control method of multi-DOF power-assistant robots for unknown external perturbation using sEMG signals. In: IEEE/RSJ international conference on intelligent robots and systems (Iros), pp 1045–1051Google Scholar
  18. 18.
    Jianda H, Qichuan D, Anbin X, Xingang Z (2015) A state-space EMG model for the estimation of continuous joint movements. IEEE Trans Industr Electron 62:4267–4275Google Scholar
  19. 19.
    Daley H, Englehart K, Hargrove L, Kuruganti U (2015) High density electromyography data of normally limbed and transradial amputee subjects for multifunction prosthetic control. Electromyogr Kinesol 22:478–484Google Scholar
  20. 20.
    Chengcheng L, Gongfa L, Guozhang J, Disi C, Honghai L (2018) Surface EMG data aggregation processing for intelligent prosthetic action recognition. Neural Comput Appl.  https://doi.org/10.1007/s00521-018-3909-z Google Scholar
  21. 21.
    Orosco E, Lopez N, Sciascio F (2013) Bispectrum-based features classification for myoelectric control. Biomed Signal Process Control 8:153–168Google Scholar
  22. 22.
    Angkoon P, Franck Q, Sylvie C, Christine S, Frank T, Yann L (2013) EMG feature evaluation for improving myoelectric pattern recognition robustness. Expert Syst Appl 40:4832–4840Google Scholar
  23. 23.
    Hudgins B, Parker P, Scott R (1993) A new strategy for multifunction myoelectric control. IEEE Trans Biomed Eng 40:82–94Google Scholar
  24. 24.
    Bowen L, Ying S, Gongfa L, Disi C, Zhaojie J (2019) Decomposition Algorithm for Depth Image of Human Health Posture Based on Brain Health. Neural comput Appl.  https://doi.org/10.1007/s00521-019-04141-9 Google Scholar
  25. 25.
    Chen X, Zhu X, Zhang D (2010) A discriminant bispectrum feature for surface electromyogram signal classification. Med Eng Phys 32:126–135Google Scholar
  26. 26.
    Graupe D, Salahi J, Zhang D (1985) Stochastic analysis of myoelectric temporal signatures for multifunctional single-site activation of prostheses and orthoses. J Biomed Eng 7:18–29Google Scholar
  27. 27.
    Yinfeng F, Honghai L, Gongfa L, Xiangyang Z (2015) A multichannel surface EMG system for hand motion recognition. Int J Humanoid Rob 12:381–509Google Scholar
  28. 28.
    Young A, Hargrove L, Kuiken T (2012) Improving myoelectric pattern recognition robustness to electrode shift by changing interelectrode distance and electrode configuration. IEEE Trans Biomed Eng 59:645–652Google Scholar
  29. 29.
    Chong T, Ying S, Gongfa L, Guozhang J, Disi C, Honghai L (2019) Research on Gesture Recognition of Smart Data Fusion Features in the IoT. Neural Comput Appl.  https://doi.org/10.1007/s00521-019-04023-0 Google Scholar
  30. 30.
    Zhaojie J, Gaoxiang O, Korsak W, Honghai L (2013) Surface EMG based hand manipulation identification via nonlinear feature extraction and classification. IEEE Sens J 13:3302–3311Google Scholar
  31. 31.
    Poosapadi A, Kumar D (2014) Computation of fractal features based on the fractal analysis of surface electromyogram to estimate force of contraction of different muscles. Comput Methods Biomech Biomed Eng 17:210–216Google Scholar
  32. 32.
    Ancillao A, Galli M, Rigoldi C, Albertini G (2014) Linear correlation between fractal dimension of surface EMG signal from Rectus Femoris and height of vertical jump. Chaos Solitons Fractals 66:120–126Google Scholar
  33. 33.
    Gongfa L, Yuesheng G, Jianyi K, Guozhang J, Liangxi X, Zehao W, Zhen L, Yuan H, Po G (2013) Intelligent control of air compressor production process. Appl Math Inf Sci 7(3):1051–1058Google Scholar
  34. 34.
    Xinpu C, Xiangyang Z, Dingguo Z (2010) A discriminant bispectrum feature for surface electromyogram signal classification. Med Eng Phys 22:126–135Google Scholar
  35. 35.
    Subasi A (2012) Classification of EMG signals using combined features and soft computing techniques. Appl Soft Comput J 12:2188–2198Google Scholar
  36. 36.
    Lukai L, Pu L, Edward A (2013) Electromyogram whitening for improved classification accuracy in upper limb prosthesis control. IEEE Trans Neural Syst Rehabil Eng 21:767–774Google Scholar
  37. 37.
    Yang L, Yantao T, Wanzhong C (2012) Modeling and classifying of sEMG based on FFT blind identification. Acta Automatica Sinica 38(1):128–134MathSciNetGoogle Scholar
  38. 38.
    Gongfa L, Peixin Q, Jianyi K, Guozhang J, Liangxi X, Po G, Zehao W, Yuan H (2013) Coke oven intelligent integrated control system. Appl Math Inf Sci 7(3):1043–1050Google Scholar
  39. 39.
    Gang W, Zhizhong W, Weiting C, Jun Z (2006) Classification of surface EMG signals using optimal wavelet packet method based on Davies-Bouldin criterion. Med Biol Eng Comput 44(10):865–872Google Scholar
  40. 40.
    Wenjun C, Gongfa L, Jianyi K, Ying S, Guozhang J, Honghai L (2018) Thermal mechanical stress analysis of ladle lining with integral brick joint. Arch Metall Mater 63:659–666Google Scholar
  41. 41.
    Andrews A, Morin E, Mclean L (2009) Optimal electrode configurations for finger movement classification using EMG. In: Engineering in medicine and biology society, pp 2987–2990Google Scholar
  42. 42.
    Hargrove L, Englehart K, Hudgins B (2008) A training strategy to reduce classification degradation due to electrode displacements in pattern recognition based myoelectric control. Biomed Signal Process Control 3(2):175–180Google Scholar
  43. 43.
    Gongfa L, Peixin Q, Jianyi K, Guozhang J, Liangxi X, Zehao W, Po G, Yuan H (2013) Influence of working lining parameters on temperature and stress field of ladle. Appl Math Inf Sci 7(2):439–448Google Scholar
  44. 44.
    Hargrove L, Englehart K, Hudgins B (2006) The effect of electrode displacements on pattern recognition based myoelectric control. Conf Proc IEEE Eng Med Biol Soc 1:2203–2206Google Scholar
  45. 45.
    Mojtaba M, Farbod R, ShMahdi A (2010) Elimination of power line noise from EMG signals using an efficient adaptive Laguerre filter. In: IEEE international conference on signals and electronic systems, pp 49–52Google Scholar
  46. 46.
    Hegen X, Huali F, Gongfa L, Guozhang J (2015) Research on steady-state simulation in dynamic job shop scheduling problem. Adv Mech Eng 7(9):1687814015604546zbMATHGoogle Scholar
  47. 47.
    Guanglin L, Yanjuan G, Dandan T, Ping Z (2011) Performance of electromyography recorded using textile electrodes in classifying arm movements. In: Conf Proc IEEE Eng Med Biol Soc, pp 4243–4246Google Scholar
  48. 48.
    Carlo L, Donald Gilmore L, Mikhail K, Serge B (2010) Filtering the surface EMG signal: movement artifact and baseline noise contamination. J Biomech 43:1573–1579Google Scholar
  49. 49.
    Dapeng Y, Jingdong Z, Jiang L, Hong L (2012) Dynamic hand motion recognition based on transient and steady-state EMG signals. Int J Humanoid Rob 9:1250–1256Google Scholar
  50. 50.
    Shenkai C, Mingtung W, Chunhao H, Jiahroung W, Lanyuen G, Wenlan W (2013) The analysis of upper limb movement and EMG activation during the snatch under various loading conditions. J Mech Med Biol 13:1350–1357Google Scholar
  51. 51.
    Md A, Muhammad I, Othman K (2011) Electromygraphy (EMG) signal based hand gesture recognition using artificial neural network (ANN). In: 4th international conference on mechatronics, Malaysia, vol 4, pp 1–6Google Scholar
  52. 52.
    Jinxian Q, Guozhang J, Gongfa L, Ying S, Bo T (2019) Surface EMG Hand Gesture Recognition System Based on PCA and GRNN. Neural Comput Appl.  https://doi.org/10.1007/s00521-019-04142-8 Google Scholar
  53. 53.
    Gongfa L, Hao W, Guozhang J, Shuang X, Honghai L (2019) Dynamic Gesture Recognition in the Internet of Things. IEEE Access 7(1):23713–23724Google Scholar
  54. 54.
    Gongfa L, Ze L, Guozhang J, Hegen X, Honghai L (2015) Numerical simulation of the influence factors for rotary kiln in temperature field and stress field and the structure optimization. Adv Mech Eng 7(6):1687814015589667Google Scholar
  55. 55.
    Veternik M, Simera M, Jakus J, Poliacek I (2013) Integration of simulated multipotential signals: the role of integration window width and of the number of spikes. Neurobiol Respir 788:265–272Google Scholar
  56. 56.
    Bu N, Hamamoto T, Tsuji T, Fukuda O (2005) FPGA implementation of a probabilistic neural network. IEICE Trans Inf Syst 88:390–397Google Scholar
  57. 57.
    Gongfa L, Jianyi K, Guozhang J, Liangxi X, Zhigang J, Gang Z (2012) Air-fuel ratio intelligent control in coke oven combustion process. Inf Int Interdiscip J 15:4487–4494Google Scholar
  58. 58.
    Ahsan M, Ibrahimy M, Khalifa O (2009) EMG signal classification for human computer interaction: a review. Eur J Sci Res 33:480–501Google Scholar
  59. 59.
    Gongfa L, Du J, Yanling Z, Guozhang J, Jianyi K (2019) Gunasekaran Manogaran. Human Lesion Detection Method Based on Image Information and Brain Signal. IEEE Access 7:11533–11542Google Scholar
  60. 60.
    Gongfa L, Jia L, Guozhang J, Honghai L (2015) Numerical simulation of temperature field and thermal stress field in the new type of ladle with the nanometer adiabatic material. Adv Mech Eng 7(4):1687814015575988Google Scholar
  61. 61.
    Chan A, Englehart K (2005) Continuous myoelectric control for powered prostheses using hidden Markov models. IEEE Trans Biomed Eng 52:121–124Google Scholar
  62. 62.
    Huang Y, Englehart K, Hudgins B, Chan A (2005) A Gaussian mixture model based classification scheme for myoelectric control of powered upper limb prostheses. IEEE Trans Biomed Eng 52:1801–1811Google Scholar
  63. 63.
    Khezri M, Jahed M (2007) Real-time intelligent pattern recognition algorithm for surface EMG signals. Biomed Eng Online 6:45Google Scholar
  64. 64.
    Disi C, Gongfa L (2017) An interactive image segmentation method in hand gesture recognition. Sensors 17(2):253Google Scholar
  65. 65.
    Yajie L, Ying S, Gongfa L, Jianyi K (2017) Simultaneous calibration: a joint optimization approach for multiple kinect and external cameras. Sensors 17(7):1491Google Scholar
  66. 66.
    Disi C, Gongfa L, Ying S, Guozhang J, Jianyi K, Jiahan L, Honghai L (2017) Fusion hand gesture segmentation and extraction based on CMOS sensor and 3D sensor. Int J Wirel Mob Comput 12(3):305–312Google Scholar
  67. 67.
    Ying S, Jiabing H (2018) Practice teaching of mechanical design based on computer media simulation. J Supercomput.  https://doi.org/10.1007/s11227-018-2255-3 Google Scholar
  68. 68.
    Qian Y, Gongfa Li, Jiangguo Z (2015) Research on the method of step feature extraction for EOD robot based on 2D laser radar. Discret Contin Dyn Syst Ser 8(6):1415–1421MathSciNetzbMATHGoogle Scholar
  69. 69.
    Gongfa L, Leilei Z, Ying S, Jianyi K (2018) Internet of Things sensors and haptic feedback for sEMG based hands. Multimed Tools Appl.  https://doi.org/10.1007/s11042-018-6293-x Google Scholar
  70. 70.
    Yang H, Gongfa L, Yaping Z, Ying S, Guozhang J (2018) Numerical simulation-based optimization of contact stress distribution and lubrication conditions in the straight worm drive. Strength Mater 50(1):157–165Google Scholar
  71. 71.
    Gongfa L, Wei M, Guozhang J, Yinfeng F, Zhaojie J, Honghai L (2015) Intelligent control model and its simulation of flue temperature in coke oven. Discret Contin Dyn Syst Ser S (DCDS-S) 8(6):1223–1237MathSciNetzbMATHGoogle Scholar
  72. 72.
    Hegen X, Huali F, Guozhang J, Gongfa L (2017) A simulation -based study of dispatching rules in a dynamic job shop scheduling problem with batch release and extended technical precedence constraints. Eur J Oper Res 257(1):13–24MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Gongfa Li
    • 1
    • 3
    • 4
    Email author
  • Jiahan Li
    • 1
  • Zhaojie Ju
    • 2
  • Ying Sun
    • 1
    • 5
  • Jianyi Kong
    • 1
    • 5
  1. 1.Key Laboratory of Metallurgical Equipment and Control Technology, Wuhan University of Science and TechnologyMinistry of EducationWuhanChina
  2. 2.School of ComputingUniversity of PortsmouthPortsmouthUK
  3. 3.Research Center for Biomimetic Robot and Intelligent Measurement and ControlWuhan University of Science and TechnologyWuhanChina
  4. 4.Institute of Precision ManufacturingWuhan University of Science and TechnologyWuhanChina
  5. 5.Hubei Key Laboratory of Mechanical Transmission and Manufacturing EngineeringWuhan University of Science and TechnologyWuhanChina

Personalised recommendations