• DocumentCode
    1748932
  • Title

    A novel approach for assessing interfacial pressure between the prosthetic socket and the residual limb for below knee amputees using artificial neural networks

  • Author

    Amali, R. ; Noroozi, S. ; Vinney, J. ; Sewell, P. ; Andrews, S.

  • Author_Institution
    Fac. of Eng., Univ. of the West of England, Bristol, UK
  • Volume
    4
  • fYear
    2001
  • fDate
    2001
  • Firstpage
    2689
  • Abstract
    So far the study of interfacial pressures between residual limb and the prosthetic socket has not led to the design of any useful tool that can assist the prosthetist to fit a prosthesis. Researchers at the UWE Bristol have found a novel methodology that can revolutionise this process. It is based on the combined application of a hybrid numerical method and experimental finite element analysis for stress analysis. This paper represents part of the development process of this tool and discusses the step forward from a two-dimensional analysis, discussed previously (2000), into a 3D symmetrical shell analysis which is intended to simulate a structured and ideal socket. The authors feel this is a logical step, which is necessary for understanding the relationship between surface stress/strain, and internal load, which causes those surface stresses. This paper emphasises the significance of this statement because it requires no knowledge of tissue properties
  • Keywords
    backpropagation; feedforward neural nets; finite element analysis; medical computing; neural nets; prosthetics; stress analysis; backpropagation; finite element analysis; interfacial pressure; knee amputees; multilayer neural networks; prosthetic socket; residual limb; surface stress analysis; Artificial neural networks; Backpropagation; Finite element methods; Internal stresses; Neural networks; Neural prosthesis; Neurons; Prosthetics; Sockets; Transducers;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
  • Conference_Location
    Washington, DC
  • ISSN
    1098-7576
  • Print_ISBN
    0-7803-7044-9
  • Type

    conf

  • DOI
    10.1109/IJCNN.2001.938795
  • Filename
    938795