Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter April 1, 2022

Stacking classifier to improve the classification of shoulder motion in transhumeral amputees

  • Amanpreet Kaur EMAIL logo


In recent years surface electromyography signals-based machine learning models are rapidly establishing. The efficacy of prosthetic arm growth for transhumeral amputees is aided by efficient classifiers. The paper aims to propose a stacking classifier-based classification system for sEMG shoulder movements. It presents the possibility of various shoulder motions classification of transhumeral amputees. To improve the system performance, adaptive threshold method and wavelet transformation have been applied for features extraction. Six different classifiers Support Vector Machines (SVM), Tree, Random Forest (RF), K-Nearest Neighbour (KNN), AdaBoost and Naïve Bayes (NB) are designed to extract the sEMG data classification accuracy. With cross-validation, the accuracy of RF, Tree and Ada Boost is 97%, 92% and 92% respectively. Stacking classifiers provides an accuracy as 99.4% after combining the best predicted multiple classifiers.

Corresponding author: Amanpreet Kaur, Electronics and Communication Department, Thapar Institute of Engineering and Technology, Patiala, Punjab 147001, India, E-mail:

  1. Research funding: Not applicable.

  2. Author contributions: Only one author.

  3. Competing interests: No conflict of interest.

  4. Informed consent: Informed consent was obtained from all individuals included in this study.

  5. Ethical approval: The local Institutional Review Board deemed the study exempt from review.


1. Nsugbe, E, Samuel, OW, Asogbon, MG, Li, G. Phantom motion intent decoding for transhumeral prosthesis control with fused neuromuscular and brain wave signals. IET Cyber Syst Robot 2021;3:77–88. in Google Scholar

2. Nishad, A, Upadhyay, A, Pachori, RB, Acharya, UR. Automated classification of hand movements using tunable-Q wavelet transform based filter-bank with surface electromyogram signals. Future Generat Comput Syst 2019;93:96–110. in Google Scholar

3. Jarrasse, N, Nicol, C, Touillet, A, Richer, F, Martinet, N, Paysant, J. Classification of phantom finger, hand and wrist voluntary gestures in upper-arm amputees with sEMG. IEEE Trans Neural Syst Rehabil Eng 2017;25:68–77. in Google Scholar PubMed

4. Amanpreet, K. Machine learning-based novel approach to classify the shoulder motion of upper limb amputees. Biocybern Biomed Eng 2019;39:857–67. in Google Scholar

5. Gini, G, Rivela, D, Frigo, CA, Belluco, P, Scannella, A, Pavan, EE. Analysis and comparison of features and algorithms to classify shoulder movements from sEMG signals. IEEE Sensor J 2018;18:3714–21.10.1109/JSEN.2018.2813434Search in Google Scholar

6. Clancy, EA, Martinez-Luna, C, Wartenberg, M, Dai, C, Farrell, T. Two degrees of freedom quasi-static EMG-force at the wrist using a minimum number of electrodes. J Electromyogr Kinesiol 2017;34:24–36. in Google Scholar PubMed PubMed Central

7. Talbot, K. Using Arduino to design a myoelectric prosthetic. 2014.Search in Google Scholar

8. Luca, CJD. Description and analysis of the EMG signal. Dans: Muscles Alive; 1985:65–101 pp.Search in Google Scholar

9. Yeom, H, Yoon, U. ECG artifact removal from surface EMG using adaptive filter algorithm. Int J Multimed Ubiquitous Eng 2012;1:533–8.Search in Google Scholar

10. Lu, G, Brittain, JS, Holland, P, Yianni, J, Green, AL, Stein, JF, et al.. Removing ECG noise from surface EMG signals using adaptive filtering. Neurosci Lett 2009;462:14–9. in Google Scholar PubMed

11. Taylor, CL. The biomechanics of control in upper-extremity prostheses. Artif Limbs 1955;2:4–25.Search in Google Scholar

12. Barton, JE. Design and evaluation of a prosthetic shoulder controller. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. EMBS. IEEE; 2011:7462–5 pp.10.1109/IEMBS.2011.6091750Search in Google Scholar PubMed PubMed Central

13. Blana, D, Kyriacou, T, Lambrecht, JM, Chadwick, EK. Feasibility of using combined EMG and kinematic signals for prosthesis control: a simulation study using a virtual reality environment. J Electromyogr Kinesiol 2016;29:21–7. in Google Scholar PubMed PubMed Central

14. Boostani, R, Moradi, MH. Evaluation of the forearm EMG signal features for the control of a prosthetic hand. Physiol Meas 2003;24:309–19. in Google Scholar PubMed

15. Subasi, A. Classification of EMG signals using combined features and soft computing techniques. Appl Soft Comput J 2012;12:2188–98. in Google Scholar

16. Willemen, T, Van Deun, D, Verhaert, V, Vandekerckhove, M, Exadaktylos, V, Verbraecken, J, et al.. An evaluation of cardiorespiratory and movement features with respect to sleep-stage classification. IEEE J Biomed Health Informatics 2014;18:661–9. in Google Scholar PubMed

17. Xia, W, Zhou, Y, Yang, X, He, K, Liu, H. Toward portable hybrid surface electromyography/a-mode ultrasound sensing for human–machine interface. IEEE Sensor J 2019;19:5219–28. in Google Scholar

18. Lolure, A. Wavelet transform based EMG feature extraction and evaluation using scatter graphs. 2015:1273. in Google Scholar

19. Eristi, H, Ucar, A, Demir, Y. Wavelet-based feature extraction and selection for classification of power system disturbances using support vector machines. Elec Power Syst Res 2010;80:743–52.10.1016/j.epsr.2009.09.021Search in Google Scholar

20. Kumar, DK, Pah, ND, Bradley, A. Wavelet analysis of surface electromyography to determine muscle fatigue. IEEE Trans Neural Syst Rehabil Eng 2003;11:400–6. 14960116.Search in Google Scholar PubMed

21. Too, J, Abdullah, AR, Zawawi, TNST, Saad, NM, Musa, H. Classification of EMG signal based on time domain and frequency domain features. Int J Hum Technol Interact 2017;1:2590–3551.Search in Google Scholar

22. Krishna, A, Thomas, P. Classification of EMG signals using spectral features extracted from dominant motor unit action potential. Int J Eng Adv Technol 2015;40:2249–8958.Search in Google Scholar

23. Weir, RF. Design of artificial arms and hands for prosthetic applications. Dans: Standard handbook of biomedical engineering and design; 2004:1–61 pp.Search in Google Scholar

24. Liu, C-L. A tutorial of the wavelet transform [En ligne]. Taiwan: National Taiwan University, Department of Electrical Engineering (NTUEE); 2010.Search in Google Scholar

25. Jiang, CF, Kuo, SL. A comparative study of wavelet denoising of surface electromyographic signals. In: Proceedings of EMBS 2007 29th annual international conference of the IEEE Engineering in Medicine and Biology Society; 2007:1868–71 pp.10.1109/IEMBS.2007.4352679Search in Google Scholar PubMed

26. Al-Qazzaz, N, Hamid Bin Mohd Ali, S, Ahmad, S, Islam, M, Escudero, J. Selection of mother wavelet functions for multi-channel EEG signal analysis during a working memory task. Sensors 2015;15:29015–35. in Google Scholar PubMed PubMed Central

27. Englehart, K1, Hudgins, BPPA. A wavelet-based continuous classification scheme for multifunction myoelectric control. IEEE Trans Biomed Eng 2001;48:302–11. in Google Scholar PubMed

28. Fadlalla, A. An experimental investigation of the impact of aggregation on the performance of data mining with logistic regression. J Inform Manag Arch 2005;42:695–707. in Google Scholar

29. Semmaoui, H, Jonathan, D, Lakhssassi, A, Sawan, M. Setting adaptive spike detection threshold for smoothed TEO based on robust statistics theory. IEEE Trans Biomed Eng 2012;59:836–41. in Google Scholar PubMed

30. Phinyomark, A, Limsakul, C, Phukpattaranont, P. EMG denoising estimation based on adaptive wavelet thresholding for multifunction myoelectric control. Proc Conf innovative technologies in intelligent systems and industrial applications; 2009:171–6 pp.10.1109/CITISIA.2009.5224220Search in Google Scholar

31. Parsaei, H, Stashuk, DW. EMG signal decomposition using motor unit potential train validity. IEEE Trans Neural Syst Rehabil Eng 2013;21:265–74. in Google Scholar

32. Kaur, A, Agarwal, R, Kumar, A. Adaptive threshold method for peak detection of surface electromyography signal from around shoulder muscles. J Appl Stat 2017;44:1–13. in Google Scholar

33. Solnik, S, Rider, P, Steinweg, K, Devita, P, Hortobgyi, T, Solnik, S, et al.. Teager–Kaiser energy operator signal conditioning improves EMG onset detection. Eur J Appl Physiol 2010;110:489–98. in Google Scholar PubMed PubMed Central

34. Solnik, S, Hortobágyi, PR, Teager, T. Kaiser energy operator signal conditioning improves EMG onset detection. Eur J Appl Physol 2010;110:489–98. in Google Scholar

35. Dyson, M, Barnes, J, Nazarpour, K. Myoelectric control with abstract decoders. J Neural Eng 2018:15. in Google Scholar PubMed

36. Quiroga, RQ, Nadasday, Z, Ben-shaul, Y. Unnsupervised spike detectionand sorting with wavelets and superparamagnetic clustering. J Neural Comput 2004;10:1661–87. in Google Scholar PubMed

37. Foster, KR, Koprowski, R, Skufca, JD. Machine learning, medical diagnosis, and biomedical engineering research – commentary. Biomed Eng Online 2014;13:94. in Google Scholar

38. Jadhav, S, He, H, Jenkins, K. An academic review: applications of data mining techniques in finance industry. Int J Soft Comput Artif Intell 2016;4:79–95.Search in Google Scholar

39. Quitadamo, LR, Cavrini, F, Sbernini, L, Riillo, F, Bianchi, L, Seri, S, et al.. Support vector machines to detect physiological patterns for EEG and EMG-based human-computer interaction: a review. J Neural Eng 2017;14:84–95. in Google Scholar PubMed

40. Li, X, Samuel, OW, Zhang, X, Wang, H, Fang, P, Li, G. A motion-classification strategy based on sEMG-EEG signal combination for upper-limb amputees. J NeuroEng Rehabil 2017;14:1–13. in Google Scholar PubMed PubMed Central

41. Karthikeyani, V. Comparison a performance of data mining algorithms (CPDMA) in prediction of diabetes disease. Int J Comput Sci Eng 2013;5:205–10.Search in Google Scholar

42. Hargrove, L, Member, S, Li, G, Englehart, K, Hargrove, L. Principal components analysis preprocessing to improve classification accuracies in pattern recognition based myoelectric control. IEEE Trans Biomed Eng 2009;56:1–28. in Google Scholar PubMed

43. Hudgins, B, Englehart, K, Parker, PA, Scott, RN. A microprocessor-based multifunction myoelectric control system. In 23rd Canadian Medical and Biological Engineering Society Conference; 1997.Search in Google Scholar

44. Trigili, E, Grazi, L, Crea, S, Accogli, A, Carpaneto, J, Micera, S, et al.. Detection of movement onset using EMG signals for upper-limb exoskeletons in reaching tasks. J NeuroEng Rehabil 2019;1:1–16. in Google Scholar PubMed PubMed Central

45. Too, J, Abdullah, AR, Saad, NM. Classification of Hand movements based on discrete wavelet transform and enhanced feature extraction. Int J Adv Comput Sci Appl 2019;10:83–9. in Google Scholar

46. Yang, D, Yang, W, Huang, Q, Liu, H. Classification of multiple finger motions during dynamic upper limb movements. IEEE J Biomed Health Inform 2017;21:134–41. in Google Scholar PubMed

47. Gaudet, G, Raison, M, Achiche, S. Classification of Upper limb phantom movements in transhumeral amputees using electromyographic and kinematic features. Eng Appl Artif Intell 2018;68:153–64. in Google Scholar

48. Pulliam, CL, Lamnrecht, JM, Kirsch, RF. EMG-Based Neural Network control of transhumeral prostheses. J Rehabil Res Dev 2013;48:739–54. in Google Scholar PubMed PubMed Central

49. Englehart, K, Hudgins, B, Parker, PA. A wavelet based continuous classification scheme for multifunction myoelectric control. 1–31.10.1109/10.914793Search in Google Scholar PubMed

50. Bonato, P, Roy, SH, Knaflitz, M, Luca, CJD. Time-frequency parameters of the surface myoelectric signal for assessing muscle fatigue during cyclic dynamic contractions. IEEE Trans Biomed Eng 2001;48:745–53. in Google Scholar PubMed

51. Tsuji, T, Hargrove, L, Leone, F, Gentile, C, Ciancio, AL, Gruppioni, E, et al.. Simultaneous sEMG classification of hand/wrist gestures and forces. Front Neurorob 2019;1:42. in Google Scholar PubMed PubMed Central

52. Flach, P. Machine learning: the art and science of algorithms that make sense of data. Cambridge, UK: Cambridge University Press; 2015:1–383 pp.Search in Google Scholar

53. Kaur, A, Kumar, A, Agarwal, R. Wavelet based machine learning technique to classify the different shoulder movement of upper limb amputee. J Biomim Biomater Biomed Eng 2017;31:32–43. in Google Scholar

54. Subasi, A, Yilmaz, M, Ozcalik, RH. Classification of EMG signals using wavelet neural network. J Neurosci Methods 2006;156:360–7. 16621003.Search in Google Scholar PubMed

55. Bankman, IN, Johnson, KO, Schneider, W. Optimal detection, classification, and superposition resolution in neural waveform recordings. IEEE Trans Biomed Eng 1993;40:836–41. in Google Scholar PubMed

56. Phinyomark, A, Limsakul, C, Phukpattaranont, P. An optimal wavelet function based on wavelet denoising for multifunction myoelectric control. In: 2009 6th International conference on electrical engineering/electronics, computer, telecommunications and information technology. IEEE; 2009:1098–101 pp.10.1109/ECTICON.2009.5137236Search in Google Scholar

57. Megahed, AI, Moussa, AM, Elrefaie, HB, Marghany, YM. Selection of a suitable mother wavelet for analyzing power system fault transients. In: IEEE Power and Energy Society 2008 general meeting: conversion and delivery of electrical energy in the 21st century. PES; 2008:1–7 pp.10.1109/PES.2008.4596367Search in Google Scholar

58. Kaur, RA, Kumar, A. A combined statistical and time–frequency approach to the analysis of electromyography signals. In: National conference on advances in metrology. Springer; 2014:19–21 pp.Search in Google Scholar

59. Kaur, A, Agarwal, R, Kumar, A. Comparison of muscles activity of abled bodied and aputee subjects for around shoulder movement. Bio Med Mater Eng 2016;27:29–37. in Google Scholar PubMed

60. Balbinot, A, Favieiro, G. A neuro-fuzzy system for characterization of arm movements. Sensors (Basel) 2013;13:2613–30. in Google Scholar PubMed PubMed Central

61. Mattioli, FE, Lamounier, EA, Cardoso, A, Soares, AB, Andrade, AO. Classification of EMG signals using artificial neural networks for virtual hand prosthesis control. In: Annual international conference of the IEEE Engineering in Medicine and Biology Society; 2011:7354–7 pp.10.1109/IEMBS.2011.6091833Search in Google Scholar PubMed

62. Soma, H, Horiuchi, Y, Gonzalez, J, Yu, W. Classification of upper limb motions from around shoulder muscle activities. Adv Appl Electromyogr 2012.10.5772/21763Search in Google Scholar

63. Hargrove, LJ, Li, G, Englehart, KB, Hudgins, BS, et al.. Principal components analysis preprocessing for improved classification accuracies. IEEE Trans Biomed Eng 2009;56:1407–14. 19473932.Search in Google Scholar PubMed

64. Rekhi, NS, Arora, AS, Singh, S, Singh, D. Multi-class SVM classification of surface EMG signal for upper limb function. In 3rd International conference on bioinformatics and biomedical engineering; 2009:1–4 pp.10.1109/ICBBE.2009.5163093Search in Google Scholar

65. Dellacasa Bellingegni, A, Gruppioni, E, Colazzo, G, Davalli, A, Sacchetti, R, Guglielmelli, E, et al.. NLR, MLP, SVM, and LDA: a comparative analysis on EMG data from people with trans-radial amputation. J NeuroEng Rehabil 2017;14:82–91. in Google Scholar PubMed PubMed Central

66. Mitchell, T. Machine learning. Portland: McGraw-Hill; 2013:1–415 pp.Search in Google Scholar

67. Zhu, X, Goldberg, AB. Introduction to semi-supervised learning. Synthesis Lect Artif Intell Mach Learn 2009;3:1–130. in Google Scholar

68. Shai, BD, Shalev-Shwartz S. Understanding machine learning: from theory to algorithms. New York, USA: Cambridge University Press; 2014:409 p.10.1017/CBO9781107298019Search in Google Scholar

69. Izabela, M, Caffé, R, Perez, PS, Baranauskas, JA. Evaluation of stacking on biomedical data artigo original evaluation of stacking on biomedical data. Biomédicos. 2014;4:67–72.Search in Google Scholar

70. Shen, S, Gu, K, Chen, XR, Yang, M, Wang, RC. Movements classification of multi-channel sEMG based on CNN and stacking ensemble learning. IEEE Access 2019;7:137489–500. in Google Scholar

71. Laksono, PW, Kitamura, T, Muguro, J, Matsushita, K, Sasaki, M, Amri, B, et al.. Minimum mapping from EMG signals at human elbow and shoulder movements into two DoF upper-limb robot with machine learning. Machines 2021;9:1–13. in Google Scholar

72. Cai, S, Chen, Y, Huang, S, Wu, Y, Zheng, H, Li, X, et al.. SVM-based classification of sEMG signals for upper-limb self-rehabilitation training. Front Neurorob 2019;13:31. in Google Scholar PubMed PubMed Central

73. Laksono, PW, Matsushita, K, Suhaimi, MSAB, Kitamura, T, Njeri, W, Muguro, J, et al.. Mapping three electromyography signals generated by human elbow and shoulder movements to two degree of freedom upper-limb robot control. Robotics 2020;9:1–14. in Google Scholar

74. Mukhopadhyay, AK, Samui, S. An experimental study on upper limb position invariant EMG signal classification based on deep neural network. Biomed Signal Process Control 2019;55:1–8.10.1016/j.bspc.2019.101669Search in Google Scholar

75. Alshdaifat, E, Al-hassan, M, Aloqaily, A. Effective heterogeneous ensemble classification: an alternative approach for selecting base classifiers. ICT Express 2020:1–8.10.1016/j.icte.2020.11.005Search in Google Scholar

76. Özkan, İA. An ensemble classifier for finger movement recognition using EMG signals. Int J Appl Math Electron Comput 2019;7:96–9.10.18100/ijamec.659781Search in Google Scholar

Received: 2020-12-16
Accepted: 2022-03-07
Published Online: 2022-04-01
Published in Print: 2022-04-26

© 2022 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 3.12.2023 from
Scroll to top button