Department of Software Technology
Vienna University of Technology
Assessment of ground reaction force patterns for human gait malfunction identification
We perform a medical computing project based on gait patterns collected from patients in an Austrian gait analysis laboratory by using two ground reaction force measurement platforms.
The project aims at an assessment of gait that is useful, on the one hand, as a support of diagnosis and therapy considerations.
On the other hand, it is intended to give clues to a model of gait, to help developing bio-feedback systems to train patients, and to find effects of multiple diseases and still active compensation.
As a major benefit, the proposed approach is exclusively based on observable data.
Hence, we do not face the tremendous effort to define a biomechanical model of gait where parameters cannot be measured precisely.
In this paper we report on identification of gait malfunction with respect to the location of ailment.
The employed classification approach is learning vector quantization which proved to be highly robust in the results provided.
Up
Comments: rauber@ifs.tuwien.ac.at