Relevant Elderly Gait Features for Functional Fitness Level Grouping

Marta S. Santos, Vera Moniz-Pereira, André Lourenço, Ana Fred, António P. Veloso


Locomotor tasks characterization plays an important role in trying to improve the quality of life of a growing elderly population. This paper focuses on this matter by trying to characterize the locomotion of two population groups with different functional fitness levels (high or low) while executing three different tasks - gait, stair ascent and stair descent. Features were extracted from gait data, and feature selection methods were used in order to get the set of features that allow differentiation between functional fitness level. Unsupervised learning was used to validate the sets obtained and, ultimately, indicated that it is possible to distinguish the two population groups. The sets of best discriminate features for each task are identified and thoroughly analysed.


  1. Alelyani, S., Tang, J., and Liu, H. (2013). Feature selection for clustering: A review. Data Clustering: Algorithms and Applications, CRC Press
  2. Begg, R. and Kamruzzaman, J. (2005). A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data. Journal of biomechanics, 38(3):401-408.
  3. Cappozzo, A., et al. (1995). Position and orientation in space of bones during movement: anatomical frame definition and determination. Clin Biomech (Bristol, Avon), 10(4):171-178.
  4. Chan, K., et al. (2002). Comparison of machine learning and traditional classifiers in glaucoma diagnosis. Biomedical Eng, IEEE Trans on, 49(9):963-974.
  5. Chau, T. (2001a). A review of analytical techniques for gait data. part 1: fuzzy, statistical and fractal methods. Gait & Posture, 13(1):49-66.
  6. Chau, T. (2001b). A review of analytical techniques for gait data. part 2: neural network and wavelet methods. Gait & Posture, 13(2):102-120.
  7. DeVita, P. and Hortobagyi, T. (2000). Age causes a redistribution of joint torques and powers during gait. J. Appl. Physiol., (88):1804-1811.
  8. Fred, A. L. (2001). Multiple Classifier Systems, chapter Finding consistent clusters in data partitions. Springer.
  9. Halkidi, M., Batistakis, Y., and Vazirgiannis, M. (2002). Cluster validity methods: Part i. SIGMOD Record.
  10. Hausdorff, J., et al.(1997). Altered fractal dynamics of gait: reduced stride-interval correlations with aging and huntingtons disease. J Appl Physiol, 82(1):262-9.
  11. Horváth, M.,et al. (2001). Kinematic and kinetic analyses of gait patterns in hemiplegic patients. Facta univ-series: Physical Edu and Sport, 1(8):25-35.
  12. Ishii, Y.,s et al. (1996). Influence of total knee replacement (tkr) design on screw-home movement: Comparison of five designs for total knee replacement prostheses. Journal of Orthopaedic Science, 1:313-317.
  13. Jain, A. K. and Dubes, R. (1988). Algorithms for Clustering Data. Prentice Hall.
  14. Janssen, D., Schllhorn, W., et al. (2011). Diagnosing fatigue in gait patterns by support vector machines and selforganizing maps. Hum Mov Sci, 30(5):966-75.
  15. Jiang, S., et al. (2010). Gait symmetry analysis based on affinity propagation clustering. In Computer and Inf Tech (CIT), IEEE 10th Int Confe on, 1673-1678.
  16. Kohle, M., et al. Clinical gait analysis by neural networks: issues and experiences. In Computer-Based Medical Systems., 1997. Proc., 10th IEEE Symp on, 138-143.
  17. Lu, T. and O'Connor, J. (1999). Bone position estimation from skin marker co-ordinates using global optimisation with joint constraints. J Biomech, 32(2):129-34.
  18. Molina, L. C., Belanche, L., and Nebot, A. (2002). Feature selection algorithms: A survey and experimental evaluation. In Proceedings of the 2002 IEEE International Conference on Data Mining, ICDM 7802, pages 306-, Washington, DC, USA. IEEE Computer Society.
  19. Moniz-Pereira, V., Carnide, F., et al. (2012). Falls in portuguese older people: procedures and preliminary results of the study biomechanics of locomotion in the elderly. Acta Reumtol. Port., 37:324-332.
  20. Mulroy, S., Gronley, J., et al. (2003). Use of cluster analysis for gait pattern classification of patients in the early and late recovery phases following stroke. Gait & Posture, 18(1):114 - 125.
  21. Murtagh, F. and Legendre, P. (2011). Ward's hierarchical clustering method: Clustering criterion and agglomerative algorithm. CoRR, abs/1111.6285.
  22. Novak, A. and Brouwer, B. (2011). Sagittal and frontal lower limb joint moments during stair ascent and descent in young and older adults. Gait Posture, 33(1):54-60.
  23. Prince, F., Corriveau, H., et al. (1997). Gait in the elderly. Gait & Posture, 5(2):128-135.
  24. Pudil, P., Novovic?ová, J., and Kittler, J. (1994). Floating search methods in feature selection. Pattern recognition letters, 15(11):1119-1125.
  25. Raudys, S. J. and Jain, A. K. (1991). Small sample size effects in statistical pattern recognition: Recommendations for practitioners. IEEE Tran. on pattern analysis and machine intelligence, 13(3):252-264.
  26. Reid, S. M., et al. (2010). Differentiation of young and older adult stair climbing gait using principal component analysis. Gait & Posture, 31(2):197 - 203.
  27. Rikli, R. E. and Jones, C. J. (1999). Development and validation of a functional fitness test for communityresiding older adults. IEEE Trans Pattern Analysis and Machine Intelligence, (7):129-161.
  28. Rose, D., Lucchese, N., and Wiersma, L. (2006). Development of a multidimensional balance scale for use with functionally independent older adults. Arch. Phys. Med. Rehabil., (87(11)):14781485.
  29. Rubenstein, L. Z. (2006). Falls in older people: epidemiology, risk factors and strategies for prevention. Age and Ageing, 35 Suppl 2:ii37ii41.
  30. Su, F.-C., Wu, W.-L., Cheng, Y.-M., and Chou, Y.-L. (2001). Fuzzy clustering of gait patterns of patients after ankle arthrodesis based on kinematic parameters. Medical Engineering & Physics, 23(2):83 - 90.
  31. Todd, D. and Skelton, C. (2004). What are the main risk factors for falls amongst older people and what are the most effective interventions to prevent these falls? Copenhagen: WHO Regional Office for Europe.
  32. Toro, B., Nester, C. J., and Farren, P. C. (2007). Cluster analysis for the extraction of sagittal gait patterns in children with cerebral palsy. Gait & Posture, 25(2):157-65.
  33. Vaughan, C. L. and O'Malley, M. J. (2005). A gait nomogram used with fuzzy clustering to monitor functional status of children and young adults with cerebral palsy. Dev Med Child Neurol, 47(6):377-83.
  34. Vinh, N., Epps, J., and Bailey, J. (2010). Information theoretic measures for clusterings comparison: Variants, properties, normalization and correction for chance. J. Mach. Learn. Res., pages 2837-2854.
  35. Winter, D. (1991). The Biomechanics and Motor Control of Human Gait: Normal,Elderly and Pathological. Waterloo: University of Waterloo Press.
  36. Xu, G., Zhang, Y., and Begg, R. (2006). Mining gait pattern for clinical locomotion diagnosis based on clustering techniques. In Proc of the 2nd int conf on Adv Data Mining and Appl, 296-307. Springer-Verlag.

Paper Citation

in Harvard Style

Santos M., Moniz-Pereira V., Lourenço A., Fred A. and P. Veloso A. (2014). Relevant Elderly Gait Features for Functional Fitness Level Grouping . In Proceedings of the International Conference on Physiological Computing Systems - Volume 1: PhyCS, ISBN 978-989-758-006-2, pages 153-160. DOI: 10.5220/0004726001530160

in Bibtex Style

author={Marta S. Santos and Vera Moniz-Pereira and André Lourenço and Ana Fred and António P. Veloso},
title={Relevant Elderly Gait Features for Functional Fitness Level Grouping},
booktitle={Proceedings of the International Conference on Physiological Computing Systems - Volume 1: PhyCS,},

in EndNote Style

JO - Proceedings of the International Conference on Physiological Computing Systems - Volume 1: PhyCS,
TI - Relevant Elderly Gait Features for Functional Fitness Level Grouping
SN - 978-989-758-006-2
AU - Santos M.
AU - Moniz-Pereira V.
AU - Lourenço A.
AU - Fred A.
AU - P. Veloso A.
PY - 2014
SP - 153
EP - 160
DO - 10.5220/0004726001530160