With age, gait functions reflected in the walking patterns degenerate and threaten the balance control mechanisms of the locomotor system. The aim of this paper is to explore applications of artificial neural networks for automated recognition of gait changes due to ageing from their respective gait-pattern characteristics. The ability of such discrimination has many advantages including the identification of at-risk or faulty gait. Various gait features (e.g., temporal-spatial, foot-ground reaction forces and lower limb joint angular data) were extracted from 12 young and 12 elderly participants during normal walking and these were utilized for training and testing on three neural network algorithms (Standard Backpropagation; Scaled Conjugate Gradient; and Backpropagation with Bayesian Regularization, BR). Receiver operating characteristics plots, sensivity and specificity results as well as accuracy rates were used to evaluate performance of the three classifiers. Cross-validation test results indicate a maximum generalization performance of 83.3% in the recognition of the young and elderly gait patterns. Out of the three neural network algorithms, BR performed superiorly in the test results with best sensitivity, selectivity and detection rates. With the help of a feature selection technique, the maximum classification accuracy of the BR attained 100%, when trained with a small subset of selected gait features. The results of this study demonstrate the capability of neural networks in the detection of gait changes with ageing and their potentials for future applications as gait diagnostics.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Price excludes VAT (USA)
Tax calculation will be finalised during checkout.
Hageman, P.A. and Blanke, D.J.,Comparison of gait of young women and elderly women, Phys Ther. Vol. 66: 1382–7, 1986.
Winter, D.A.,The Biomechanics and Motor Control of Human Gait: Normal, Elderly and Pathological, University of Waterloo Press, Waterloo, 1991.
Öberg, T., Karsznia, A. and Öberg, K.,Joint angle parameters in gait: Reference data for normal subjects, 10-79 years of age, J Rehab Res Dev. Vol. 31: 199–213, 1994.
Judge, J. O., Davis, R. B., and Öunpuu, S.,Step length reductions in advanced age: The role of ankle and hip kinetics, J Gerontol Med Sci. vol. 51: 303–12, 1996.
Fildes, B.Injuries among older people: Falls at home and pedestrian accidents, Dove Publications, Melbourne, 1994.
Wu, W.-L., Su, F.-C., Chou, C. K.,Potential of the back propagation neural networks in the assessment of gait patterns in ankle arthrodesis, Clin Biomech. Vol. 15: 143–5, 2000.
Chau, T.,A review of analytical techniques for gait data. Part 2: neural network and wavelet methods, Gait Posture, vol. 13: 102–20, 2001.
Schöllhorn, W. I.Applications of artificial neural nets in clinical biomechanics, Clin Biomech. Vol. 19: 876–98, 2004.
Holzreiter, S. H. and Kohle, M. E.,Assessment of gait pattern using neural networks, J Biomech, vol. 26: 645–51, 1993.
Barton, J. G., Lees, A.,An application of neural networks for distinguishing gait patterns on the basis of hip-knee joint angle diagrams, Gait Posture, vol. 5: 28–33, 1997.
Begg, R., Kamruzzaman, J.,A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data, J Biomech. Vol. 8: 401–408, 2005.
Begg, R. K., Sparrow, W. A., Lythgo, N. D.,Time-domain analysis of foot-ground reaction forces in negotiating obstacles, Gait Posture. Vol. 7: 99–109, 1998.
Nigg, B. M., Fisher, V., Ronsky, J. L.,Gait characteristics as a function of age and gender, Gait Posture. Vol. 2: 213–20, 1994.
Whittle, M.,Gait Analysis: An Introduction. Butterworth Heinemann, Oxford, 1991.
Fogel, D. B. and Robinson, C. J.,Computational Intelligence. IEEE, USA, 2003.
Reich, Y. and Barai, S. V.,Evaluating machine learning models for engineering problems, Artif Intell Eng. Vol. 13: 257–72, 1999.
White, H. and Racine, J.,Statistical inference, the bootstrap, and neural-network modelling with application to foreign exchange rates, IEEE Trans Neural Net. Vol. 12: 657–73, 2001.
Sepulveda, F., Wells, D., Vaughan, C. L.,A neural network representation of electromyography and joint dynamics in human gait, J Biomech. vol. 26: 101–9, 1993.
Hetrz, J., Krogh, A. and Palmer, R. G.,Introduction to the Theory of Neural Computation, Addison-Wesley, 1991.
Begg, R. K., Kamruzzaman J., Sarker, R.,Movement pattern recognition using neural networks, Chapter 10, In (Begg, Kamruzzaman & Sarker eds.) Neural Networks in Health Care: Potential and Challenges, IGI Publishing: Hershey, PA, 217–237, 2006.
Hagan, M. T., Demuth, H. B., Beale, M. H.,Neural Network Design. PWS Publishing, Boston, 1996.
Moller, A. F.,A scaled conjugate gradient algorithm for fast supervised learning, Neural Net. Vol. 6: 525–33, 1993.
Bishop, C. M.,Neural Network for Pattern Recognition. Oxford University Press, New York, 1995.
Mackay, D. J. C.,A practical Bayesian framework for backpropagation networks, Neural Comp. Vol. 4: 415–47, 1992.
Foresee, F. D., and Hagan, M. T.,Gauss-Newton approximation to Bayesian learning. Proc. IEEE ICNN, vol. 3: 1930–5, 1997.
More, J. J.,The Levenberg-Marquart algorithm: implementation and theory, in: G.A. Watson, ed.,Numerical analysis.Lecture Notes in Mathematics 630. Springer-Verlag: London, 1977.
Cybenko, G.,Approximation by superpositions of a sigmoidal function, Mathematical Control Signal Systems, Vol. 2: 303–314, 1989.
Chan, K., Lee, T. W., Sample, P. A., Goldbaum, M. H., Weinreb, R. N., and Sejnowski, T. J.,Comparison of Machine Learning and Traditional Classifiers in Glaucoma Diagnosis, IEEE Trans Biomed Eng. Vol. 49: 963–74, 2002.
Pang, C. C. C., Upton, A. R. M., Shine, G., Kamath, M. V.,A comparison of algorithms for detection of spikes in the electroencephalogram, IEEE Trans Biomed Eng. Vol. 50: 521–6, 2003.
Kecman, V.,Learning and soft computing: support vector machines, neural networks and fuzzy logic models. IEEE, New Jersey, 2002.
Yom-Tov, E., and Inbar, G. F.,Feature selection for the classification of movements from single movement-related potentials, IEEE Trans Neural Sys. Vol. 10: 170–7, 2002.
Rights and permissions
About this article
Cite this article
Begg, R., Kamruzzaman, J. Neural networks for detection and classification of walking pattern changes due to ageing. Australas. Phys. Eng. Sci. Med. 29, 188–195 (2006). https://doi.org/10.1007/BF03178892
- gait analysis
- neural networks
- feature selection