Article

This study aimed to use the plantar pressure insole for estimating the
three-dimensional ground reaction force (GRF) as well as the frictional torque
(T(F)) during walking. Eleven subjects, six healthy and five patients with ankle
disease participated in the study while wearing pressure insoles during several
walking trials on a force-plate. The plantar pressure distribution was analyzed
and 10 principal components of 24 regional pressure values with the stance time
percentage (STP) were considered for GRF and T(F) estimation.
Both linear and
non-linear approximators were used for estimating the GRF and T(F) based on two
learning strategies using intra-subject and inter-subjects data.
The RMS error
and the correlation coefficient between the approximators and the actual patterns
obtained from force-plate were calculated. Our results showed better performance
for non-linear approximation especially when the STP was considered as input.
The least errors were observed for vertical force (4%) and anterior-posterior force
(7.3%), while the medial-lateral force (11.3%) and frictional torque (14.7%) had
higher errors. The result obtained for the patients showed higher error;
nevertheless, when the data of the same patient were used for learning, the
results were improved and in general slight differences with healthy subjects
were observed. In conclusion, this study showed that ambulatory pressure insole
with data normalization, an optimal choice of inputs and a well-trained nonlinear
mapping function can estimate efficiently the three-dimensional ground reaction
force and frictional torque in consecutive gait cycle without requiring a force-plate.
CI - Copyright (c) 2010 Elsevier B.V. All rights reserved.

Langue : ANGLAIS