Advertisement

Foot Plantar Pressure Estimation Using Artificial Neural Networks

  • Elias Xidias
  • Zoi Koutkalaki
  • Panagiotis Papagiannis
  • Paraskevas Papanikos
  • Philip AzariadisEmail author
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 467)

Abstract

In this paper, we present a novel approach to estimate the maximum pressure over the foot plantar surface exerted by a two-layer shoe sole for three distinct phases of the gait cycle. The proposed method is based on Artificial Neural Networks and can be utilized for the determination of the comfort that is related to the sole construction. Input parameters to the proposed neural network are the material properties and the thicknesses of the sole layers (insole and outsole). A set of simulation experiments has been conducted using analytic finite elements analysis in order to compile the necessary dataset for the training and validation of the neural network. Extensive experiments have shown that the developed method is able to provide an accurate alternative (more than 96 %) compared to the highly expensive, with respect to computational and human resources, approaches based on finite element analysis.

Keywords

Artificial neural network Foot plantar pressure Mechanical comfort 

Notes

Acknowledgments

This research has been co-financed by the European Union (European Social Fund - ESF) and Greek national funds through the Operational Program “Education and Lifelong Learning” of the National Strategic Reference Framework (NSRF) - Research Funding Program “ARISTEIA”.

References

  1. 1.
    Kirtley, C.: Clinical Gait – Analysis, Theory and Practice. Elsevier, Philadelphia (2006)Google Scholar
  2. 2.
    Fong, D.T.P., Hong, Y., Li, J.X.: Cushioning and lateral stability functions of cloth sport shoes. Sports Biomech. 6(3), 407–417 (2007)CrossRefGoogle Scholar
  3. 3.
    Papagiannis, P., Koutkalaki, Z., Azariadis, P.: Footwear plantar mechanical comfort: physical measures and modern approaches to their approximation. In: 5th International Conference on Advanced Materials and Systems, 23–25 October, Bucharest, Romania (2014)Google Scholar
  4. 4.
    Razak, A., Zayegh, A., Begg, K., Wahab, Y.: Foot plantar pressure measurement system: a review. Sens. 12(7), 9884–9912 (2012)CrossRefGoogle Scholar
  5. 5.
    Gefen, A.: Pressure-sensing devices for assessment of soft tissue loading under bony prominences: Technological concepts and clinical utilization. Wounds 19, 350–362 (2007)Google Scholar
  6. 6.
    MacWilliams, B.A., Armstrong, P.F.: Clinical applications of plantar pressure measurement in pediatric orthopedics. In: Gait, P. (ed.) A New Millennium in Clinical Care and Motion Analysis Technology, Chicago, IL, USA, pp. 143–150 (2000)Google Scholar
  7. 7.
    Azariadis P.: Finite Element analysis in footwear design. In: Goonetilleke, R. (eds) The Science of Footwear, pp. 321–337. Taylor & Francis Group (2012)Google Scholar
  8. 8.
    Hertz, J., Krogh, A., Palmer, R.G.: Introduction to the theory of neural computation, 9th edn. Wesley Publishing Company, Reading (1994)Google Scholar
  9. 9.
    Carter, M.: Minds and Computers: An Introduction to the Philosophy of Artificial Intelligence. University Press, Edinburgh (2007). ISBN 9780748620999Google Scholar
  10. 10.
    Kaczmarczyk, K., Wit, A., Krawczyk, M., Zaborski, J.: Gait classification in post-stroke patients using artificial neural networks. Gait Posture 30(2), 207–210 (2009)CrossRefGoogle Scholar
  11. 11.
    Schöllhorn, W.: Applications of artificial neural nets in clinical biomechanics. Clin. Biomech. 10(9), 876–898 (2004)CrossRefGoogle Scholar
  12. 12.
    Chau, T.: A review of analytical techniques for gait data. Part 2: neural network and wavelet methods. Gait Posture 13(2), 102–120 (2001)CrossRefGoogle Scholar
  13. 13.
    Kose, A., Cereatti, A., Della Croce, U.: Bilateral step length estimation using a single inertial measurement unit attached to the pelvis. J. NeuroEng. Rehabil. 9, 1–10 (2012)CrossRefGoogle Scholar
  14. 14.
    Rupérez, M., Martin-Guerrero, J., Monserrat, C., Alemany, S., Alcañi, Z.: Artificial neural networks for predicting dorsal pressures on the foot surface while walking. Expert Syst. Appl. 39(5), 5349–5357 (2012)CrossRefGoogle Scholar
  15. 15.
    Baum, E.: On the capabilities of multilayer perceptrons. J. Complex. 4(3), 193–215 (1988)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Twomey, J., Smith, A., Redfern, M.: A predictive model for slip resistance using artificial neural networks. IIE Trans. 27(3), 374–381 (1995)CrossRefGoogle Scholar
  17. 17.
    Barton, J., Lees, A.: Comparison of shoe insole materials by neural network analysis. Med. Biol. Eng. Comput. 34(6), 453–459 (1996)CrossRefGoogle Scholar
  18. 18.
    Kirk, B., Carr, T., Haake, S., Manson, G.: Using neural networks to understand relationships in the traction of studded footwear on sports surfaces. J. Biomech. 39(1), 175–183 (2006)Google Scholar
  19. 19.
    Vable, M.: Mechanics of Materials, 2nd edn. Michigan Technological University, Houghton (2014)Google Scholar
  20. 20.
    Koutkalaki, Z., Papagiannis, P., Azariadis, P., Papanikos, P., Kyratzi, S., Zissis, D., Lekkas, D., Xidias, E.: Towards a foot bio-model for performing finite element analysis for footwear design optimization using a Cloud infrastructure. CAD Appl. 12, 1–12 (2015). doi: 10.1080/16864360.2015.1014728 Google Scholar
  21. 21.
    Dennis, W., Ruck, K., Kabrisky, R.: Feature selection using a multilayer perceptron. J. Neural Netw. Comput. 2(2), 40–48 (1990)Google Scholar
  22. 22.
    Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Prentice-Hall, Upper Saddle River (2009)Google Scholar
  23. 23.
    Sola, J.: Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Trans. Nucl. Sci. 44(3), 1464–1468 (1997)CrossRefGoogle Scholar
  24. 24.
    Cassandra, R., Littman, M., Zhang, N.: Incremental pruning: A simple, fast, exact method for partially observable Markov decision processes. In: Uncertainty in Artificial Intelligence (UAI) (1997)Google Scholar
  25. 25.
    Karlik, B., Olgac, A.V.: Performance analysis of various activation functions in generalized MLP architectures of neural networks. Int. J. Artif. Intell. Expert Syst. 1, 111 (2010)Google Scholar
  26. 26.
    Gomes, S., Ludermir, T.: Optimization of the weights and asymmetric activation function family of neural network for time series forecasting. Expert Syst. Appl. 40, 6438–6446 (2013)CrossRefGoogle Scholar
  27. 27.
    Souza, B., Brito, N., Neves, W.: Comparison between back propagation and RPROP algorithms applied to fault classification in transmission lines. In: IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541), pp. 2913–2918 (2004)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2016

Authors and Affiliations

  • Elias Xidias
    • 1
  • Zoi Koutkalaki
    • 1
  • Panagiotis Papagiannis
    • 1
  • Paraskevas Papanikos
    • 1
  • Philip Azariadis
    • 1
    Email author
  1. 1.Department of Product and Systems Design EngineeringUniversity of the AegeanErmoupoliGreece

Personalised recommendations