Special Issue on Biosignal Sensing and Intelligent Information ProcessingNo Access

SVM MODELS FOR DIAGNOSING BALANCE PROBLEMS USING STATISTICAL FEATURES OF THE MTC SIGNAL

Department of Electrical Engineering, The University of Melbourne, Parkville Campus, Melbourne, Victoria 3010, Australia

Search for more papers by this author

REZAUL BEGG

Centre for Ageing, Rehabilitation, Exercise and Sport, Victoria University, Melbourne, Victoria 8001, Australia

Search for more papers by this author

, and

MARIMUTHU PALANISWAMI

Department of Electrical Engineering, The University of Melbourne, Parkville Campus, Melbourne, Victoria 3010, Australia

Search for more papers by this author

https://doi.org/10.1142/S1469026808002314Cited by:9 (Source: Crossref)

Abstract

Trip-related falls are a major problem in the elderly population and research in the area has received much attention recently. The focus has been on devising ways of identifying individuals at risk of sustaining such falls. The main aim of this work is to explore the effectiveness of models based on Support Vector Machines (SVMs) for the automated recognition of gait patterns that exhibit falling behavior. Minimum toe clearance (MTC) during continuous walking on a treadmill was recorded on 10 healthy elderly and 10 elderly with balance problems and with a history of tripping falls. Statistical features obtained from MTC histograms were used as inputs to the SVM model to classify between the healthy and balance-impaired subjects. The leave-one-out technique was utilized for training the SVM model in order to find the optimal model parameters. Tests were conducted with various kernels (linear, Gaussian and polynomial) and with a change in the regularization parameter, C, in an effort to identify the optimum model for this gait data. The receiver operating characteristic (ROC) plots of sensitivity and specificity were further used to evaluate the diagnostic performance of the model. The maximum accuracy was found to be 90% using a Gaussian kernel with σ² = 10 and the maximum ROC area 0.98 (80% sensitivity and 100% specificity), when all statistical features were used by the SVM models to diagnose gait patterns of healthy and balance-impaired individuals. This accuracy was further improved by using a feature selection method in order to reduce the effect of redundant features. It was found that two features (standard deviation and maximum value) were adequate to give an improved accuracy of 95% (90% sensitivity and 100% specificity) using a polynomial kernel of degree 2. These preliminary results are encouraging and could be useful not only for diagnostic applications but also for evaluating improvements in gait function in the clinical/rehabilitation contexts.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

R. K. Begg, W. A. Sparrow and N. D. Lythgo, Gait Posture 7, 99 (1998), DOI: 10.1016/S0966-6362(97)00039-8. Crossref, Google Scholar
D. A. Winter , The Biomechanics and Motor Control of Human Gait: Normal, Elderly and Pathological ( Waterloo Press , Canada , 1991 ) . Google Scholar
B. Fildes , Injuries Among Older People: Falls at Home and Pedestrian Accidents ( Dove Publications , Melbourne , 1994 ) . Google Scholar
R. K. Begget al., Gait Posture 25(2), 191 (2006), DOI: 10.1016/j.gaitpost.2006.03.008. Crossref, Google Scholar
M. P. Kadaba, H. K. Ramakrishnan and M. E. Wooten, J. Orthop. Res. 8, 383 (1990), DOI: 10.1002/jor.1100080310. Crossref, Google Scholar
S. Ounpuu, J. R. Gage and R. B. Davis, J. Padeatr. Orthop. 11, 341 (1991). Crossref, Google Scholar
M. H. Schwartz and A. Rozumalski, J. Biomech. 38, 107 (2005). Crossref, Google Scholar
A. L. Bell, R. A. Brand and D. R. Pedersen, Hum. Mov. Sci. 8, 3 (1989), DOI: 10.1016/0167-9457(89)90020-1. Crossref, Google Scholar
S. H. Holzreiter and M. E. Kohle, J. Biomech. 26, 645 (1993), DOI: 10.1016/0021-9290(93)90028-D. Crossref, Google Scholar
W. L. Wu, F. C. Su and C. K. Chou, Clin. Biomech. 15, 143 (2000), DOI: 10.1016/S0268-0033(99)00037-6. Crossref, Google Scholar
J. G. Barton and A. Lees, Gait Posture 5, 28 (1997), DOI: 10.1016/S0966-6362(96)01070-3. Crossref, Google Scholar
B. Scholkopf , C. J. C. Burges and A. J. Smola , Advances in Kernel Methods: Support Vector Learning ( MIT Press , Cambridge, MA , 1999 ) . Google Scholar
B. Scholkopf and A. J. Smola , Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond ( MIT Press , Cambridge, MA , 2002 ) . Google Scholar
R. K. Begg, M. Palaniswami and B. Owen, IEEE Trans. Biomed. Eng. 52, 828 (2005), DOI: 10.1109/TBME.2005.845241. Crossref, Google Scholar
R. K. Begget al., MFC histogram and poincare plot images for automated gait detection, Proc. Int. Conf. Intelligent Sensing and Information Processing1 (2004) pp. 368–372. Google Scholar
F. C. Anderson and M. G. Pandy, J. Biomech. 123(5), 381 (2001). Crossref, Google Scholar
V. N. Vapnik , The Nature of Statistical Learning Theory , 2nd edn. ( Springer , New York , 2000 ) . Crossref, Google Scholar
N. Cristianini and J. Shawe-Taylor , An Introduction to Support Vector Machines and Other Kernel-based Learning Methods ( Cambridge University Press , New York , 2000 ) . Crossref, Google Scholar
K. Chanet al., IEEE Trans. Biomed. Eng. 49, 963 (2002). Crossref, Google Scholar
D. P. Bertsekas , Constrained Optimization and Lagrange Multiplier Methods , Optimization and Neural Computation Series ( Athena Scientific , Belmont, MA , 1996 ) . Google Scholar
J. Kamruzzaman and R. K. Begg, IEEE Trans. Biomed. Eng. 52, 828 (2006). Google Scholar
K. Englehartet al., Med. Eng. Phys. Intell. Data Anal. Electromyogr. Electroneurogr. 21(Special Issue), 431 (1999). Google Scholar
C. R. Hicks , Fundamental Concepts in the Design of Experiments ( Saunders College Publishing , New York , 1993 ) . Google Scholar
G. D. Tourassiet al., Med. Phys. 28(12), 2394 (2001), DOI: 10.1118/1.1418724. Crossref, Google Scholar