Expert System Design Based on Wavelet Transform and Non-Linear Feature Selection

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 222)


Electromyogram (EMG) is the record of the electrical excitation of the skeletal muscles, which is initiated and regulated by the central, and peripheral nervous system. EMGs have non-stationary properties. EMG signals of isometric contraction for two different abnormalities namely ALS (Amyotrophic Lateral Sclerosis) which is coming under Neuropathy and Myopathy. Neuropathy relates to the degeneration of neural impulse whereas myopathy relates to the degeneration of muscle fibers. There are two issues in the classification of EMG signals. In EMG’s diseases recognition, the first and the most important step is feature extraction. In this paper, we have selected Symlet of order five of mother wavelet for EMG signal analysis and later six non-linear features have been used to classify using Support Vector Machine. After feature extraction, feature matrix is normalized in order to have features in a same range. Simply, linear SVM classifier was trained by the train–train data and then used for classifying the train-test data. From the experimental results, Lyapunov exponent and Hurst exponent is the best feature with higher accuracy comparing with the other features, whereas features like Capacity Dimension, Correlation Function, Correlation Dimension, Probability Distribution & Correlation Matrix are useful augmenting features.


ALS Hurst exponent Lyapunov exponent Myopathy 


  1. 1.
    Boisset S, Goubel F (1972) Integrated electromygraphy activity and muscle work. J Applied Physiol 35:695–702Google Scholar
  2. 2.
    Plonsey R (1974) The active fiber in a volume conductor. IEEE Trans Biomed Eng 21:371–381CrossRefGoogle Scholar
  3. 3.
    De Luca C, (2006) ‘Electromyography’. Encyclopedia Of Medical Devices and Instrumentation. In: John G (ed) Webster, Wiley, New yorkGoogle Scholar
  4. 4.
    DeLuca CJ (1993) Use of the surface EMG signal for performance evaluation of back muscle. Muscle Nerve 16:210–216CrossRefGoogle Scholar
  5. 5.
    Jones RS et al (1988) On-line analysis of neuromuscular function. In: Proceeding of IEEE Engineering in Medicine Biology, vol 10, p 1607Google Scholar
  6. 6.
    Mengi Y, Liu B, Liu Y (2001) A comprehensive nonlinear analysis of electromyogram engineering in medicine and biology society. In: Proceedings of the 23rd annual international conference of the IEEE, vol 2. pp 1078–1081 (Nov 2002)Google Scholar
  7. 7.
    Small GJ, Jones NB, Fothergill JC, Mocroft AP (2002) Chaos as a possible model of electromyographic activity simulation 98. International conference on (Conf. Publ No 457) pp 27–34Google Scholar
  8. 8.
    Erfanian A, Chizeck HJ, Hashemi RM (1996) Chaotic activity during electrical stimulation of paralyzed muscle engineering in medicine and biology society bridging disciplines for biomedicine. In: Proceedings of the 18th Annual International Conference of the IEEE, vol 4. pp 1756–1757 (Aug 2002)Google Scholar
  9. 9.
    Bodruzzaman M, Devgan S, Kari S (1992) Chaotic Classification Of Electromyographic (Emg) Signals Via Correlation Dimension Measurement Southeastcon ‘92. In: Proceedings IEEE, vol 1. pp 95–98 (Aug 2002)Google Scholar
  10. 10.
    Yang H, Wang D, Wang J (2006) Linear and non-linear features of surface EMG during fatigue and recovery period. Engineering in Medicine and Biology Society, IEEE-EMBS 2005.In: 27th annual international conference, pp 5804–5807, Apr 2006Google Scholar
  11. 11.
    Englehart K, Hudgins B, Parker PA (2001) A wavelet-based continuous classification scheme for multifunction myoelectric control. IEEE Trans Biomed Eng 48(3):302–311CrossRefGoogle Scholar
  12. 12.
    Aldroubi A, Unser M (eds) (1996) Wavelets in medicine and biology. CRC Press, New YorkMATHGoogle Scholar
  13. 13.
    Rioul O, Vetterli M (1991) Wavelets and signal processing. IEEE Signal Process Mag, pp 14–38 Oct 1991Google Scholar
  14. 14.
    DeLuca CJ (1993) Use of the surface EMG signal for performance evaluation of back muscle. Muscle Nerve 16:210–216CrossRefGoogle Scholar
  15. 15.
    Jones RS et al (1988) On-line Analysis of Neuromuscular Function. In: Proceeding IEEE engineering in medicinal biology, vol l0. p 1607 (Nov 1988)Google Scholar

Copyright information

© Springer India 2013

Authors and Affiliations

  1. 1.Department of Biomedical EngineeringNational Institute of TechnologyRaipurIndia
  2. 2.Department of Electrical EngineeringSGSITSIndoreIndia

Personalised recommendations