Bekir KARLIK

3217

Differentiating type of muscle movement via AR modelling and neural network classification

Differentiating type of muscle movement via AR modelling and neural network classification

The aim of this study is to classify electromyogram (EMG) signals for controlling multifunction proshetic devices. An artificial neural network (ANN) implementation was used for this purpose. Autoregressive (AR) parameters of a1 , a2, a3,a4 and their signal power obtained from different arm muscle motions were applied to the input of ANN, which is a multilayer perceptron. At the output layer, for 5000 iterations, six movements were distinguished at a high accuracy of 97.6%.
PDF

___

  • [1] D. Graupe, Functional Separation of EMG Signals via ARMA Identi cation Methods for Prosthesis ControlPurposes", IEEE Trans. Syst. Man Cybern., SMC-5, (1975), 252-259.
  • [2] D. Graupe, J. Magnuses, and A. Beex, Microprocessor System for Multifunctional Control of Upper-LimbsProstheses", IEEE Trans. Automat. Control., AC-23, Aug. (1978), 538-544.
  • [3] D. Graupe, J. Salahi and K. H. Kohn, Multifunction Prosthesis and Orthosis Control via MicrocomputerIdenti cation of Temporal Pattern Di erences in Single-Site Myoelectric Signals", J. Biomed. Eng., 4, (1982),17-22.
  • [4] George N. Saridis and Thomas Gotee, EMG Pattern Analysis and Classi cation for a Prosthetic Arm", IEEETrans. Biomed. Eng., BME-29 no: 6, June (1982), 403-412
  • [5] H. Schmeild, The I.N.A.I.L. Experience Fitting Upper-Limb dysmelia Patients With Myoelectric Control",Bull. Prosth. Res., BPR 10-27, (1997), 17-42.
  • [6] C. Almstrom, P. Herbets, and L. Korner, Experiences With Swedish Multifunction Prosthetic Hands Con-trolled by Pattern Recognition of Multiple Myoelectric Signals", Int. Orthopased, 5, (1981), 15-21.
  • [7] S. C. Jacobsen, D. F. Knutti, R. T. Johnson, H. H. Sears, Development of The Utah Arti cal Arm", IEEETrans. Biomed. Eng., BME-29, April (1982), 249.
  • [8] P. J. Cardo, Controlling Multiple Degree of Freedo Powered Prosthesis", in Proc. IEEE Conf. Frontiers ofEng. and Comp. in Health Care, Columbus, OH, (1983), 151-155.
  • [9] M. Kelly, P. Parker, and R. N. Scott, The Application of Neural Networks to Myoelectric Signal Analysis: aPreliminary Study", IEEE Trans. Biom. Eng., BME-37, (1990), 221-227.
  • [10] B. Hudgins, P. Parker, R. N. Scott, A New Strategy for Multifunction Myoelectric Control", IEEE Trans.Biomedical Eng., 40, no: 1, January, (1993), 82-94.
  • [11] A. Kohen, Biomedical Signal Processing", vol. 1, (CRC Press, 1986), p. 3-5, 81-89.
  • [12] B. Karlık, H. Pastacı, M. Korürek, Myoelectric Neural Networks Signal Analysis", in Proc. IEEE 7th.Melecon'94, Antalya, Turkey, 1, April (1994), 262-264.
  • [13] T. J. Sejnowski, C. Rosenberg, Parallel Networks That Learn to Pronounce English Text", Complex Syst., 1,(1987), 145-168b
  • [14] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, Parallel Distributed Processing Explorations in theMicrostructures of Cognition", vol.1, (Eds.) D. E. Rumelhant and J. L. Mc Clalland, (MA: MIT Press,Cambridge 1986), p. 318-362.
  • [15] B. Karlık, Myoelectric Control of Multifunction Prosthesis by Using Arti cial Neural Networks", Ph.D. Thesis,Department of Electrical Eng., Institute of Science, Yldz Technical University, Istanbul, Turkey, 1994.
Turkish Journal of Electrical Engineering and Computer Sciences-Cover
  • ISSN: 1300-0632
  • Yayın Aralığı: Yılda 6 Sayı
  • Yayıncı: TÜBİTAK
Arşiv
Sayıdaki Diğer Makaleler

Differentiating type of muscle movement via AR modelling and neural network classification

Bekir KARLIK