Prediction of elasticity constants in small biomaterial samples such as bone. A comparison between classical optimization techniques and identification with artificial neural networks

Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine

Volumn 218, Issue 6, 2004, Pages 389-405

  Stussi E ^a   Lucchinetti, E ^b  

^a SWISS FEDERAL INSTITUTE OF TECHNOLOGY   (Switzerland)

^b UNIVERSITY OF ZURICH   (Switzerland)

Author keywords

Elasticity; Inverse problems; Neural networks; Optimization

Indexed keywords

ALGORITHMS; BIOMECHANICS; ELASTIC MODULI; ELASTICITY; INVERSE PROBLEMS; MATHEMATICAL MODELS; MEASUREMENT ERRORS; NEURAL NETWORKS; OPTIMIZATION; TISSUE; BIOLOGICAL MATERIALS; BONE; SIGNAL TO NOISE RATIO;

BACKCALCULATION; ELASTICITY CONSTANT;

BONE; INVERSE PROBLEMS;

CLASSICAL OPTIMIZATION; ELASTICITY CONSTANTS; IDENTIFICATION APPROACH; IDENTIFICATION PROCEDURE; IRREGULAR GEOMETRIES; MATERIAL PARAMETER; OPTIMIZATION PROBLEMS; ROBUST OPTIMIZATION;

BIOMATERIAL;

ALGORITHM; ANIMAL; ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL MODEL; BONE; CHEMISTRY; COMPARATIVE STUDY; COMPUTER SIMULATION; ELASTICITY; EVALUATION; HUMAN; MATERIALS TESTING; MECHANICAL STRESS; METHODOLOGY; PHYSIOLOGY; REPRODUCIBILITY; SENSITIVITY AND SPECIFICITY; STATISTICAL MODEL; STIMULATION; VALIDATION STUDY;

ALGORITHMS; ANIMALS; BIOCOMPATIBLE MATERIALS; BONE AND BONES; COMPUTER SIMULATION; ELASTICITY; HUMANS; MATERIALS TESTING; MODELS, BIOLOGICAL; MODELS, STATISTICAL; NEURAL NETWORKS (COMPUTER); PHYSICAL STIMULATION; REPRODUCIBILITY OF RESULTS; SENSITIVITY AND SPECIFICITY; STRESS, MECHANICAL;

EID: 13744264059     PISSN: 09544119     EISSN: None     Source Type: Journal    
DOI: 10.1243/0954411042632090     Document Type: Article

References (20)

1. Oomens, C. W., van Ratingen, M. R., Janssen, J. D., Kok, J. J. and Hendriks, M. A. A numerical-experimental method for a mechanical characterization of biological materials. J. Biomechanics, 1993, 26, 617-621.
2. Moulton, M. J., Creswell, L. L., Actis, R. L., Myers, K. W., Vannier, M. W., Szabo, B. A. and Pasque, M. K. An inverse approach to determining myocardial material properties. J. Biomechanics, 1995, 28, 935-948.
3. Op Den Camp, O. M. G. C., Oomens, C. W. J., Veldpaus, F. E. and Janssen, J. D. An efficient algorithm to estimate material parameters of biphasic mixtures. Int. J. for Numer. Meth. in Engng, 1999, 45, 1315-1331.
4. Schwarz, U. S., Balaban, N. Q., Riveline, D., Bershadsky, A., Geiger, B. and Safran, S. A. Calculation of forces at focal adhesions from elastic substrate data: the effect of localized force and the need for regularization. Biophys. J., 2002, 83, 1380-1394.
5. Fletcher, R. Practical Methods of Optimization, 1987 (John Wiley, Chichester).
6. Scales, L. E. Introduction to Nonlinear Optimization, 1985 (Springer-Verlag, New York).
7. Whitley, D. A genetic algorithm tutorial. Statistics and Computing, 1994, 4(2), 65-85.
8. Goldberg, D. E. and Deb, K. Special issue on genetic algorithms. Comput. Meth Appl. Mech. and Engng, 2000, 186 2-4), 121-124.
9. Kirkpatrick, S., Gelatt, C. D. and Vecchi, M. P. Optimization by simulated annealing. Science, 1983, 220, 671-680.
10. Haykin, S. Neural Networks: a Comprehensive Foundation, 2nd edition, 1999 (Prentice-Hall, Upper Saddle River, New Jersey).
11. Schalko, R. J. Artificial Neural Networks, 1997 (McGraw-Hill, New York).
12. Lucchinetti, E. and Stüssi, E. Measuring the flexural rigidity in non-uniform beams using an inverse problem approach. Inverse Problems, 2002, 18, 837-857.
13. Burnett, D. S. Finite Element Analysis, from Concepts to Applications, 1987 (Addison-Wesley, Reading, Massachusetts).
14. Hughes, J. R. The Finite Element Method - Linear Static and Dynamic Finite Element Analysis, 1987 (Prentice-Hall, Englewood Cliffs, New Jersey).
15. Nelder, J. A. and Mead, R. A simplex method for function minimization. Computer J., 1965, 7, 308-313.
16. Optimization Toolbox User's Guide, Version 4, Release 12.1, 2001 (The MathWorks, Inc., Natick, Massachusetts).
17. Cybenko, G. Continuous valued neural networks with two hidden layers are sufficient. Math. Controls, Signals and Syst., 1989, 2, 303-314.
18. Hornik, K., Stinchcombe, M. and White, H. Multilayer feedforward networks are universal approximators. Neural Networks, 1989, 2, 359-366.
19. Neural Network Toolbox User's Guide, Version 4, Release 12, 2001 (The MathWorks, Inc., Natick, Massachusetts).
20. Beck, J. V. and Arnold, K. J. Parameter Estimation in Engineering and Science, 1977 (Wiley, New York).