Regression Techniques for the Prediction of Lower Limb Kinematics

[+] Author and Article Information
J. Y. Goulermas1

Department of Electrical Engineering and Electronics,  University of Liverpool, Brownlow Hill, Liverpool L69 3GJ, UKj.y.goulermas@liverpool.ac.uk

D. Howard, L. Ren

Centre for Rehabilitation and Human Performance Research,  University of Salford, Salford M5 4WT, UK and School of Computing, Science and Engineering,  University of Salford, Salford M5 4WT, UK

C. J. Nester, R. K. Jones

Centre for Rehabilitation and Human Performance Research,  University of Salford, Salford M5 4WT, UK and School of Healthcare Professions,  University of Salford, Salford M5 4WT, UK


Corresponding author: Department of Electrical Engineering and Electronics University of Liverpool Brownlow Hill Liverpool L69 3GJ UK

J Biomech Eng 127(6), 1020-1024 (Jul 04, 2005) (5 pages) doi:10.1115/1.2049328 History: Received April 18, 2005; Revised July 04, 2005

This work presents a novel and extensive investigation of mathematical regression techniques, for the prediction of laboratory-type kinematic measurements during human gait, from wearable measurement devices, such as gyroscopes and accelerometers. Specifically, we examine the hypothesis of predicting the segmental angles of the legs (left and right foot, shank and thighs), from rotational foot velocities and translational foot accelerations. This first investigation is based on kinematic data emulated from motion-capture laboratory equipment. We employ eight established regression algorithms with different properties, ranging from linear methods and neural networks with polynomial support and expanded nonlinearities, to radial basis functions, nearest neighbors and kernel density methods. Data from five gait cycles of eight subjects are used to perform both inter-subject and intra-subject assessments of the prediction capabilities of each algorithm, using cross-validation resampling methods. Regarding the algorithmic suitability to gait prediction, results strongly indicate that nonparametric methods, such as nearest neighbors and kernel density based, are particularly advantageous. Numerical results show high average prediction accuracy (ρ=0.980.99,RMS=5.63°2.30°,MAD=4.43°1.52° for inter∕intra-subject testing). The presented work provides a promising and motivating investigation on the feasibility of cost-effective wearable devices used to acquire large volumes of data that are currently collected only from complex laboratory environments.

Copyright © 2005 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Prediction to actual signal correlation plot (ρ=0.9732) for the GRN output θrf. The thick and thin lines represent the best and ideal linear fits, respectively



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In