Skip to main content
SpringerLink
Log in

An automatic feature extraction and fusion model: application to electromyogram (EMG) signal classification

  • Regular Paper
  • Published:
International Journal of Multimedia Information Retrieval Aims and scope Submit manuscript

Abstract

In this paper, we present a real-time feature extraction and fusion model for an automated staging of electromyogram signals-generalizing canonical correlation analysis (CCA). The proposed method is capable of capturing multiple view information (i.e., feature matrices) generated from signals. Our algorithm employs an optimization technique to derive sets of statistical features among the paired views based on which possible variations of signals have been demonstrated. Next, discrete wavelet transformation is performed on multiple views to create domain independent views which are then subjected to CCA optimization. The estimated two sets of statistically independent features from two independent analysis are concentrated through two recently proposed fusion models, and then, we evaluate global feature matrices. Further it is validated statistically for \(p<0.05\). The proposed algorithm is then analyzed and compared with state-of-the-art methods. Results indicate that the proposed approach outperforms many other methods in terms of accuracy, specificity and sensitivity, which are 98.80, 99.0 and 98.0%, respectively. Thus, the proposed algorithm is suitable for large-scale applications and expedite diagnosis research.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. The average parameter values are estimated from confusion matrices in terms of mean \(\mu \) and standard deviation \(\sigma \) from k—cross-validation techniques.

References

  1. Sun BY, Zhang XM, Li J, Mao XM (2010) Feature fusion using locally linear embedding for classification. IEEE Trans Neural Netw 21(1):163–168

    Article  Google Scholar 

  2. Haghighat M, Abdel-Mottaleb M, Alhalabi W (2016) Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition. IEEE Trans Inf Forensics Secur 11:1984–1996

    Article  Google Scholar 

  3. Shen X, Sun Q (2015) Orthogonal multiset canonical correlation analysis based on fractional-order and its application in multiple feature extraction and recognition. Neural Process Lett 42(2):301–316

    Article  Google Scholar 

  4. Sun QS, Zeng SG, Liu Y, Heng PA, Xia DS (2005) A new method of feature fusion and its application in image recognition. Pattern Recognit 38(12):2437–2448

    Article  Google Scholar 

  5. Liu M, Zhang D, Shen D (2016) Inherent structure based multi- view learning with multi-template feature representation for Alzheimers disease diagnosis. IEEE Trans Biomed Eng 63(7):1473–1482

    Article  Google Scholar 

  6. Shen X, Sun Q (2014) A novel semi-supervised canonical correlation analysis and extensions for multi-view dimensionality reduction. J Vis Commun Image Represent 25(8):1894–1904

    Article  Google Scholar 

  7. Xia T, Tao D, Mei T, Zhand Y (2010) Multiview spectral embedding. IEEE Trans Syst Man Cybern B Cybern 40(6):1436–1446

    Google Scholar 

  8. Bickel S, Scheffer T (2004) Multi-view clustering. In: Proceedings of the international conference on data mining, p 1926

  9. Chu JU, Moon I, Lee YJ, Kim SK, Mun MS (2007) A supervised feature-projection-based real-time EMG pattern recognition for multifunction myoelectric hand control. IEEE/ASME Trans Mechatron 12(3):282–290

    Article  Google Scholar 

  10. Mandic D P, Obradovic D, Kuh A, Adali T, Trutschell U, Golz M, Chambers J. Mandic (2005) Data fusion for modern engineering applications: an overview. In: International conference on artificial neural networks, Berlin, Heidelberg

  11. Fu Y, Cao L, Guo G, Huang TS (2009) Multiple feature fusion by subspace learning. In: Proceedings of the ACM international conference on content-based image and video retrieval, New York, NY, USA, pp 127–134

  12. 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):1–10

    Article  Google Scholar 

  13. Dutta L, Hazarika A, Bhuyan M (2016) Microcontroller based E-nose for gas classification without using ADC. Sens Transducers 202(7):38–45

    Google Scholar 

  14. Yuan YH, Sun QS, Zhou Q, Xia DS (2011) A novel multiset integrated canonical correlation analysis framework and its application in feature fusion. Pattern Recognit 44(5):1031–1040

    Article  MATH  Google Scholar 

  15. Peng Y, Daoqiang Z, Zhang J (2010) A new canonical correlation analysis algorithm with local discrimination. Neural Process Lett 31(1):1–15

    Article  Google Scholar 

  16. Hotelling H (1936) Relations between two sets of variates. Biometrika 28(3/4):321–377

    Article  MATH  Google Scholar 

  17. Correa NM, Adali T, Yi-Ou L, Calhoun VD (2010) Canonical correlation analysis for feature-based fusion of biomedical imaging modalities and its application to detection of associative networks in schizophrenia. IEEE J Sel Top Signal Process 2(6):39–50

    Article  Google Scholar 

  18. Khushaba RN (2014) Correlation analysis of electromyogram signals for multiuser myoelectric interfaces. IEEE Trans Neural Syst Rehabil Eng 22(4):745–755

    Article  Google Scholar 

  19. DeClercq W, Vergult A, Vanrumste B, Paesschen WV, Huffel SV (2006) Canonical correlation analysis applied to remove muscle artifacts from the electroencephalogram. IEEE Trans Biomed Eng 53(12):2583–2587

    Article  Google Scholar 

  20. Lin Z, Zhang C, Wu W, Gao X (2006) Frequency recognition based on canonical correlation analysis for SSVEP-based BCIs. IEEE Trans Biomed Eng 53(12):2610–2614

    Article  Google Scholar 

  21. Yousefi J, Wright AH (2014) Characterizing EMG data using machine-learning tools. Comput Biol Med 51(1):1–13

    Article  Google Scholar 

  22. Kaur G, Arora AS, Jain VK (2009) Multi-class support vector machine classifier in EMG diagnosis. WSEAS Trans Signal Process 5(12):379–389

    Google Scholar 

  23. Subasi A (2012) Medical decision support system for diagnosis of neuromuscular disorders using DWT and fuzzy support vector machines. Comput Biol Med 42(8):806–815

    Article  Google Scholar 

  24. Subasi A (2013) Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput Biol Med 43(5):576–586

    Article  Google Scholar 

  25. Subasi A (2012) Classification of EMG signals using combined features and soft computing techniques. Appl soft comput 12(8):2188–2198

    Article  Google Scholar 

  26. Kamali T, Boostani R, Parsaei H (2014) A multi-classifier approach to MUAP classification for diagnosis of neuromuscular disorders. IEEE Trans Neural Syst Rehabil Eng 22(1):192–200

    Article  Google Scholar 

  27. Doulah ABMSU, Fattah SA, Zhu WP, Ahmad MO (2014) Ahmad, Wavelet Domain Feature Extraction scheme based on dominant motor unit action potential of EMG signal for neuromuscular disease classification. IEEE Trans Biomed Circuits Syst 8(2):155–164

    Article  Google Scholar 

  28. Katsis CD, Exarchos T, Papaloukas C, Goletsis Y, Fotiadis DI, Sarmas I (2007) A two-stage method for MUAP classification based on EMG decomposition. Comput Biol Med 31(9):1232–1240

    Article  Google Scholar 

  29. Englehart K, Hudgins B, Philip A (2001) A wavelet-based continuous classification scheme for multifunction myoelectric control. IEEE Trans Biomed Eng 48(3):302–311

    Article  Google Scholar 

  30. Dobrowolski AP, Wierzbowski M, Tomczykiewicz K (2012) Multiresolution MUAPs decomposition and SVM-based analysis in the classification of neuromuscular disorders. Comput Methods Programs BioMed 107(3):393–403

    Article  Google Scholar 

  31. Bentaleb Y (2010) An algorithm of wavelets for the pretreatment of EMG biomedical signals. Int J Contemp Eng Sci 3(6):285–294

    Google Scholar 

  32. Abel EW, Meng H, Forster A, Holder D (2006) Singularity characteristics of needle EMG IP signals. IEEE Trans Biomed Eng 53(2):219–225

    Article  Google Scholar 

  33. Hazarika A, Barthakur M, Dutta L, Bhuyan M (2016) Two-fold feature extraction technique for biomedical signals classification. In: Proceedings of conference on inventive computation technologies

  34. Hazarika A, Barthakur M, Dutta L, Bhuyan M (2016) Fusion of projected feature for classification of EMG patterns. In: Proceedings of conference on recent advances and innovations in engineering

  35. Naik G, Selvan S, Nguyen H (2016) Single-channel EMG classification with ensemble-empirical-mode-decomposition-based ICA for diagnosing neuromuscular disorders. IEEE Trans Neural Syst Rehabil Eng 24(7):734–743

    Article  Google Scholar 

  36. Nikolic M (2001) Detailed analysis of clinical electromyography signals: EMG decomposition, findings and firing pattern analysis in controls and patients with myopathy and amytrophic lateral sclerosis. Ph.D. thesis, University of Copenhagen, Copenhagen, Denmark

  37. Kakarala R, Philip OO (2001) Signal analysis using a multiresolution form of the singular value decomposition. IEEE Trans Image Process 10(5):724–735

    Article  MathSciNet  MATH  Google Scholar 

  38. Johnson RA, Dean WW (1992) Applied multivariate statistical analysis. Prentice hall, Englewood Cliffs

    MATH  Google Scholar 

  39. Hardoon DR, Sandor S, John ST (2004) Canonical correlation analysis: an overview with application to learning methods. Neural comput. 16(12):2639–2664

    Article  MATH  Google Scholar 

  40. Sun L, Shuiwang J, Jieping Y (2011) Canonical correlation analysis for multilabel classification: a least-squares formulation, extensions, and analysis. IEEE Trans Pattern Anal Mach Intell 33(1):194–200

    Article  Google Scholar 

  41. Arya R, Jaiswal S (2015) Design of low pass FIR filters using Kaiser window function with variable parameter Beta. Int J Multidiscip Curr Res p 3

  42. Sargin ME, Ycel Y, Engin E (2007) Audiovisual synchronization and fusion using canonical correlation analysis. IEEE Trans Multimedia 9(7):1396–1403

    Article  Google Scholar 

  43. Zhang C, Wang H, Fu R (2014) Automated detection of driver fatigue based on entropy and complexity measures. IEEE Trans Intell Transp Syst 15(1):168–177

    Article  Google Scholar 

  44. Hassan M, Boudaoud S, Terrien J, Karlsson B, Marque C (2011) Combination of canonical correlation analysis and empirical mode decomposition applied to denoising the labor electrohysterogram IEEE Trans. Biomed Eng 58(9):2441–2447

    Google Scholar 

  45. Hassan AR, Aynal Haque Md (2016) Computer-aided obstructive sleep apnea screening from single-lead electrocardiogram using statistical and spectral features and bootstrap aggregating. Biocybern Biomed Eng 36(1):256–266

    Article  Google Scholar 

  46. Gokgoz E, Subasi A (2015) Comparison of decision tree algorithms for EMG signal classification using DWT. Biomed Signal Process Control 18:138–144

    Article  Google Scholar 

  47. Subasi A (2015) A decision support system for diagnosis of neuromuscular disorders using evolutionary support vector machines. Signal Image Video Process 9(2):399–408

    Article  Google Scholar 

  48. Bruser C, Diesel J, Zink MDH, Winter S, Schauerte P, Leonhardt S (2013) Automatic detection of atrial fibrillation in cardiac vibration signals biomedical and health informatics. IEEE J Biomed Health Inf 17(1):162–171

    Article  Google Scholar 

  49. Barthakur M (2015) Detection and classification of peripheral motor neuropathy: a signal processing approach as support system to neurophysiologists. Ph.D thesis, Tezpur University

  50. Barthakur M, Hazarika A, Bhuyan M (2014) Rule based fuzzy approach for peripheral motor neuropathy (PMN) diagnosis based on NCS data. In: Proceeding of conference on recent advances and innovations in eng 1–9

  51. Barthakur M, Hazarika A, Bhuyan M (2013) A novel technique of neuropathy detection and classification by using artificial neural network (ANN). In: Proceeding of conference on advance signal process and communication 706–713

Download references

Acknowledgements

The authors would like to thank Mantoo Kaibarta and Rajesh Barman for their helps during signal analysis. The authors would also like to thank the anonymous reviewers for their valuable suggestions and comments on the article.

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Tezpur University, Sonitpur, Assam, India

    Anil Hazarika, Lachit Dutta, Meenakshi Boro & Manabendra Bhuyan

  2. Department of Neurophysiology, Guwahati Neurological Research Centre, Guwahati, Assam, India

    Mausumi Barthakur

Authors
  1. Anil Hazarika
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lachit Dutta
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Meenakshi Boro
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mausumi Barthakur
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Manabendra Bhuyan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anil Hazarika.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hazarika, A., Dutta, L., Boro, M. et al. An automatic feature extraction and fusion model: application to electromyogram (EMG) signal classification. Int J Multimed Info Retr 7, 173–186 (2018). https://doi.org/10.1007/s13735-018-0149-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13735-018-0149-z

Keywords

Search

Navigation