Skip to main content

Binary Particle Swarm Optimization-Based Feature Selection for Predicting the Class of the Knee Angle from EMG Signals in Lower Limb Movements

The performance of a binary particle swarm optimization-based feature selection (BPSOFS) for predicting the class of the knee angle (KA) from myoelectric signals in lower limb movements was examined. Surface EMG (sEMG) signals were recorded from the vastus lateralis and biceps femoris muscles while performing a task of standing up from and sitting down on the chair. The knee angle was measured using a goniometer and quantized into five levels/classes. The sEMG signals were segmented using overlapped windowing. Twenty features per muscle were extracted and fed to a support vector machine (SVM) classifier. Grid selection was done to set the parameters of the classifier. In our study, the KA was first divided into five levels/classes, and the KA class was predicted from the features of sEMG signals using the SVM classifier. Subsequently, BPSOFS was implemented, and the classification accuracy was measured using a reduced feature set. The performance of three different initialization techniques, namely small, large, and mixed initializations, were compared. A paired t test was applied to compare the performance of the SVM classifier with BPSOFS and with the SVM classifier using all the features. The results indicated that BPSOFS achieves a classification accuracy of 90.92% utilizing only 30% of the total features (P > 0.05).

This is a preview of subscription content, access via your institution.


  1. I. Guyon and A. Elisseeff, “An introduction to variable and feature selection,” J. Mach. Learn. Res., 3, 1157–1182 (2003),

    Article  Google Scholar 

  2. H. Banka and S. Dara, “A Hamming distance based binary particle swarm optimization (HDBPSO) algorithm for high dimensional feature selection, classification and validation,” Pattern Recognit. Lett., 52, 94–100 (2015).

    Article  Google Scholar 

  3. R. Eberhart and J. Kennedy, “A new optimizer using particle swarm theory,” In: MHS’95. Proc. Sixth Int. Symp. Micro Machine Human Sci., IEEE, 39–43 (1995).

  4. R. Boostani and M. H. Moradi, “Evaluation of the forearm EMG signal features for the control of a prosthetic hand,” Physiol. Meas., 24, No. 2, 309–319 (2003),

    Article  PubMed  Google Scholar 

  5. L. Hargrove, K. Englehart, and B. Hudgins, “A training strategy to reduce classification degradation due to electrode displacements in pattern recognition based myoelectric control,” Biomed. Signal Process. Control, 3, No. 2, 175–180 (2008).

    Article  Google Scholar 

  6. H.-P. Huang, Y.-H. Liu, L.-W. Liu, and C.-S. Wong, “EMG classification for prehensile postures using cascaded architecture of neural networks with self-organizing maps,” Proc. IEEE Int. Robot. Autom., 1, 1497–1502 (2003),

    Article  Google Scholar 

  7. M. Zardoshti-Kermani, B. C. Wheeler, K. Badie, and R. M. Hashemi, “EMG feature evaluation for movement control of upper extremity prostheses,” IEEE Trans. Rehabil. Eng., 3, No. 4, 324–333 (1995).

    Article  Google Scholar 

  8. A. Phinyomark, F. Quaine, S. Charbonnier, et al., “EMG feature evaluation for improving myoelectric pattern recognition robustness,” Expert Syst. Appl., 40, No. 12, 4832–4840 (2013),

    Article  Google Scholar 

  9. K. Englehart, B. Hudgins, P. A. Parker, and M. Stevenson, “Classification of the myoelectric signal using time-frequency based representations,” Med. Eng. Phys., 21, No. 6–7, 431–438 (1999),

    CAS  Article  PubMed  Google Scholar 

  10. J.-U. Chu, I. Moon, and M.-S. Mun, “A real-time EMG pattern recognition system based on linear-nonlinear feature projection for a multifunction myoelectric hand,” IEEE Trans. Biomed. Eng., 53, No. 11, 2232–2239 (2006).

    Article  Google Scholar 

  11. K. E. Member, B. H. Member, P. A. Parker, and S. Member, “A wavelet based continuous classification scheme for multifunction myoelectric control,” IEEE Trans. Biomed. Eng., 48, No. 3, 1–31 (2001).

    Google Scholar 

  12. H. Huang, F. Zhang, L. J. Hargrove, et al., “Continuous locomotion-mode identification for prosthetic legs based on neuromuscular--mechanical fusion,” IEEE Trans. Biomed. Eng., 58, No. 10, 2867–2875 (2011),

  13. R. Gupta and R. Agarwal, “Electromyographic signal-driven continuous locomotion mode identification module design for lower limb prosthesis control,” Arab. J. Sci. Eng. (2018),

  14. R. Gupta, I. S. Dhindsa, and R. Agarwal, “Continuous angular position estimation of human ankle during unconstrained locomotion,” Biomed. Signal Process. Control, 60, 101968 (2020).

  15. R. Gupta and R. Agarwal, “Continuous human locomotion identification for lower limb prosthesis control,” CSI Trans. ICT, 6, 1–15 (2017),

    Article  Google Scholar 

  16. H. Huang, T. A. Kuiken, and R. D. Lipschutz, “A strategy for identifying locomotion modes using surface electromyography,” IEEE Trans. Biomed. Eng., 56, No. 1, 65–73 (2009),

    Article  PubMed  PubMed Central  Google Scholar 

  17. A. L. Delis, J. L. A. Carvalho, A. F. Da Rocha, et al., “Estimation of the knee joint angle from surface electromyographic signals for active control of leg prostheses,” Physiol. Meas., 30, No. 9, 931–946 (2009),

    Article  PubMed  Google Scholar 

  18. F. Zhang, P. Li, Z.-G. Hou, et al., “sEMG-based continuous estimation of joint angles of human legs by using BP neural network,” Neurocomputing, 78, No. 1, 139–148 (2012).

    Article  Google Scholar 

  19. I. S. Dhindsa, R. Agarwal, and H. S. Ryait, “Performance evaluation of various classifiers for predicting knee angle from electromyography signals,” Expert Syst., 36, No. 3, e12381 (2019),

  20. C.-L. Huang and J.-F. Dun, “A distributed PSO–SVM hybrid system with feature selection and parameter optimization,” Appl. Soft Comput., 8, No. 4, 1381–1391 (2008).

    Article  Google Scholar 

  21. Eberhart and Y. Shi, “Particle swarm optimization: developments, applications and resources,” Proc. 2001 Congr. Evol. Comput., 1, 81–86 (2001),

  22. J. Kennedy and R. C. Eberhart, “A discrete binary version of the particle swarm algorithm,” 1997 IEEE Int. Conf. Sys., Man Cybern. Comput. Cybern. Simul., 5, 4104–4108 (1997),

  23. I. S. Dhindsa, R. Agarwal, and H. S. Ryait, “Principal component analysis-based muscle identification for myoelectric-controlled exoskeleton knee,” J. Appl. Stat., 44, No. 10, 1707–1720 (2017),

    Article  Google Scholar 

  24. B. Frericks, “The recommendations for sensors and sensor placement procedures for surface electromyography,” SENIAM Deliv. 8, Eur. Recomm. Surf. Electromyogr., 15–53 (1999).

  25. L. J. Hargrove, G. Li, K. B. Englehart, and B. S. Hudgins, “Principal components analysis preprocessing for improved classification accuracies in pattern-recognition-based myoelectric control,” IEEE Trans. Biomed. Eng., 56, No. 5, 1407–1414 (2009),

    Article  PubMed  Google Scholar 

  26. B. Hudgins, P. Parker, R. N. Scott, B. Hudgins, P. Parker, and R. Scott, “A new strategy for multifunction myoelectric control,” IEEE Trans. Biomed. Eng., 40, No. 1, 82–94 (1993),

    CAS  Article  PubMed  Google Scholar 

  27. J. Virmani, V. Kumar, N. Kalra, and N. Khandelwal, “SVM-based characterization of liver ultrasound images using wavelet packet texture descriptors,” J. Digit. Imaging, 26, No. 3, 530–543 (2013),

    Article  PubMed  Google Scholar 

  28. A. Ganapathiraju, J. E. Hamaker, and J. Picone, “Application of support vector machines to speech recognition,” IEEE Trans. Signal Process., 52, No. 8, 2348–2355 (2004),

    Article  Google Scholar 

  29. S. Tong and D. Koller, “Support vector machine active learning with applications to text classification,” J. Mach. Learn. Res., 2, No. Nov, 45–66 (2001),

  30. S.-W. Lin, K.-C. Ying, S.-C. Chen, and Z.-J. Lee, “Particle swarm optimization for parameter determination and feature selection of support vector machines,” Expert Syst. Appl., 35, No. 4, 1817–1824 (2008),

    Article  Google Scholar 

  31. M. Pardo and G. Sberveglieri, “Classification of electronic nose data with support vector machines,” Sensors Actuators B Chem., 107, No. 2, 730–737 (2005).

    CAS  Article  Google Scholar 

  32. S.-C. Chen, S.-W. Lin, and S.-Y. Chou, “Enhancing the classification accuracy by scatter-search-based ensemble approach,” Appl. Soft Comput., 11, No. 1, 1021–1028 (2011).

    Article  Google Scholar 

  33. C.-W. Hsu, C.-C. Chang, and C.-J. Lin, “A practical guide to support vector classification” (2003).

  34. R. Gupta and R. Agarwal, “sEMG interface design for locomotion identification,” Int. J. Electr. Comput. Eng., 11, No. 2, 66–75 (2017).

    Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to R. Gupta.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Dhindsa, I.S., Gupta, R. & Agarwal, R. Binary Particle Swarm Optimization-Based Feature Selection for Predicting the Class of the Knee Angle from EMG Signals in Lower Limb Movements. Neurophysiology 53, 109–119 (2022).

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI:


  • lower limb movements
  • knee joint angle
  • surface electromyography
  • feature selection
  • particle swarm optimization
  • support vector machine