Neural Computing and Applications

, Volume 28, Supplement 1, pp 945–952 | Cite as

Classifying neuromuscular diseases using artificial neural networks with applied Autoregressive and Cepstral analysis

Original Article
First Online:
Received:
Accepted:

Abstract

The aim this study was to classify neuromuscular disorders using artificial neural networks (ANNs). To achieve this target, EMG signals received from normal, neuropathy, and myopathy subjects were recorded. To represent the signals adequately, matching feature parameters were obtained using Autoregressive (AR) and Cepstral analysis; executing principal component analysis was used to reduce the number of data obtained from the AR and Cepstral analysis. Following these data was used to train the ANN. Multilayer perceptron- (MLP) and radial basis function-based networks were used in the training sessions. According to our results, the combination of AR with 4-6-3 MLP topology yielded the area below the receiver operating characteristic curve of 0.954303, which is considered to be within the limits of the acceptable range.

Keywords

Electromyography (EMG) Principal component analysis (PCA) Autoregressive (AR) Cepstral Multilayer perceptron (MLP) Radial basis function (RBF) 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    Güler NF, Koçer S (2005) Use of support vector machines and neural network in diagnosis of neuromuscular disorders. J Med Syst 29(3):271–284CrossRefGoogle Scholar
  2. 2.
    De Luca CJ (1993) Use of the surface EMG signal for performance evaluation of back muscles. Muscle Nerve 16(2):210–216CrossRefGoogle Scholar
  3. 3.
    Kutilek P, Mares J, Hybl J, Socha V, Schlenker J, Stefek A (2015) Myoelectric arm using artificial neural networks to reduce cognitive load of the user. Neural Comput Appl. doi: 10.1007/s00521-015-2074-x Google Scholar
  4. 4.
    Koçer S (2010) Classifying myopathy and neuropathy neuromuscular diseases using artificial neural networks. Int J Pattern Recognit Artif Intell 24(05):791–807CrossRefGoogle Scholar
  5. 5.
    Kamali T, Reza B, Hossein P (2014) A multi-classifier approach to MUAP classification for diagnosis of neuromuscular disorders. IEEE Trans Neural Syst Rehabil Eng 22(1):191–200CrossRefGoogle Scholar
  6. 6.
    Makki B, Hosseini MN, Seyyedsalehi SA (2010) An evolving neural network to perform dynamic principal component analysis. Neural Comput Appl 19(3):459–463CrossRefGoogle Scholar
  7. 7.
    Taouali O, Elaissi I, Messaoud H (2012) Online identification of nonlinear system using reduced kernel principal component analysis. Neural Comput Appl 21(1):161–169CrossRefGoogle Scholar
  8. 8.
    Castaño A, Fernández-Navarro F, Riccardi A, Hervás-Martínez C (2015) Enforcement of the principal component analysis–extreme learning machine algorithm by linear discriminant analysis. Neural Comput Appl. doi: 10.1007/s00521-015-1974-0 Google Scholar
  9. 9.
    Michael Kelly F, Parker P, Scott RN (1990) The application of neural networks to myoelectric signal analysis: a preliminary study. IEEE Trans Biomed Eng 37.3:221–230CrossRefGoogle Scholar
  10. 10.
    Kamaruddin NA, Khalid PI, Shaameri AZ (2015) The use of surface electromyography in muscle fatigue assessments—a review. J Technol 74(6):119–124Google Scholar
  11. 11.
    Scheme E, Englehart K (2014) On the robustness of EMG features for pattern recognition based myoelectric control; a multi-dataset comparison. In: Engineering in Medicine and Biology Society (EMBC), 2014 36th annual international conference of the IEEE. IEEEGoogle Scholar
  12. 12.
    Vicente JG, Cinthia I (2014) Optimal Autoregressive orders for myopathic electromyograms. In: Engineering in Medicine and Biology Society (EMBC), 2014 36th annual international conference of the IEEE. IEEEGoogle Scholar
  13. 13.
    Güler NF, Koçer S (2005) Classification of EMG signals using PCA and FFT. J Med Syst 29(3):241–250CrossRefGoogle Scholar
  14. 14.
    Zhang J, Thurmon EL, Rahul S (2014) Classifying lower extremity muscle fatigue during walking using machine learning and inertial sensors. Ann Biomed Eng 42(3):600–612CrossRefGoogle Scholar
  15. 15.
    Koçer S (2010) Classification of EMG signals using neuro-fuzzy system and diagnosis of neuromuscular diseases. J Med Syst 34(3):321–329CrossRefGoogle Scholar
  16. 16.
    Shalu George K, Sivanandan KS, Mohandas KP (2012) Fuzzy logic and probabilistic neural network for EMG classification—a comparitive study. Int J Eng Res Technol 1(5):1–7Google Scholar
  17. 17.
    Xie HB, Huang H, Wu J, Liu L (2015) A comparative study of surface EMG classification by fuzzy relevance vector machine and fuzzy support vector machine. Physiol Meas 36(2):191CrossRefGoogle Scholar
  18. 18.
    Mokhlesabadifarahani B, Gunjan VK (2015) Introduction to EMG technique and feature extraction. In: EMG signals characterization in three states of contraction by fuzzy network and feature extraction. Springer, Singapore, pp 1–9Google Scholar
  19. 19.
    Addison D, Stefan W, Arevian G, (2003) A comparison of feature extraction and selection techniques. In: Proceedings of international conference on artificial neural networks (supplementary proceedings)Google Scholar
  20. 20.
    Englehart K et al (1999) Classification of the myoelectric signal using time-frequency based representations. Med Eng Phys 21(6):431–438CrossRefGoogle Scholar
  21. 21.
    Doulah ABMSU, Shaikh AF (2014) Neuromuscular disease classification based on mel frequency cepstrum of motor unit action potential. In: International conference on Electrical Engineering and Information and Communication Technology (ICEEICT), 2014. IEEEGoogle Scholar
  22. 22.
    Micera S et al (1999) A hybrid approach to EMG pattern analysis for classification of arm movements using statistical and fuzzy techniques. Med Eng Phys 21(5):303–311CrossRefGoogle Scholar
  23. 23.
    Proakis JG, Manolakis D (2006) Digital signal processing: principles, algorithms and applications. 4th edn. Pearson, Upper Saddle River, NJGoogle Scholar
  24. 24.
    Rangayyan RM (2015) Biomedical signal analysis: a case-study approach. IEEE press series on biomedical engineering, vol 33. Wiley, New YorkGoogle Scholar
  25. 25.
    Bishop CM (1995) Neural networks for pattern recognition. Clarendon Press, Oxford University, New YorkGoogle Scholar
  26. 26.
    Hudgins B, Parker P, Scott RN (1993) A new strategy for multifunction myoelectric control. IEEE Trans Biomed Eng 40(1):82–94CrossRefGoogle Scholar
  27. 27.
    Chowhan SS, Shinde GN (2009) Evaluation of statistical feature encoding techniques on iris images. WRI World congress on computer science and information engineering, 2009, vol 7. IEEEGoogle Scholar
  28. 28.
    Englehart K et al (1999) Classification of the myoelectric signal using time-frequency based representations. Med Eng Phys 21(6):431–438CrossRefGoogle Scholar
  29. 29.
    Haykin S (2004) A comprehensive foundation. Neural NetwGoogle Scholar
  30. 30.
    Atal BS (1974) Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification. J Acoust Soc Am 55(6):1304–1312CrossRefGoogle Scholar
  31. 31.
    McClelland JL, Rumelhart DE, PDP Research Group (1987) Parallel distributed processing, vol 2. MIT Press, Cambridge, MAGoogle Scholar
  32. 32.
    Prechelt L (1998) Automatic early stopping using cross validation: quantifying the criteria. Neural Netw 11:761–767CrossRefGoogle Scholar
  33. 33.
    Costa JD, Gander RE (1993) MES classification using artificial neural networks and chaos theory. In: Proceedings of 1993 international joint conference on neural networks, 1993. IJCNN’93-Nagoya, vol 3. IEEEGoogle Scholar
  34. 34.
    Basheerand IA, Hajmeer M (2000) Artificial neural networks: fundamentals, computing, design, and application. J Microbiol Methods 43(1):3–31CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  1. 1.Computer EngineeringNecmettin Erbakan UniversityMeramTurkey

Personalised recommendations