Author(s)

A. Bertani, A. Cappello, F. Catani, M.G. Benedetti & S. Giannini

Abstract

Statistical pattern recognition techniques were applied to discriminate between healthy and Hal fool children through ground reaction force (GRF) measurements. 28 young subjects (age 11.8 ± 1.8) with symptomatic flexible flat foot, and 13 healthy subjects (age 10.1 ± 1.4) took part on this preliminar study. The Karhunen-Locvc expansion with Fukunaga-Koonlz normalization was applied to each GRF component to extract concise and discriminant features from the original data. The best performances of the classifying process were obtained using three principal components of both vertical and fore-aft GRF projections. Both linear and quadratic Hayes classifiers were designed with 9.2% and 4.9% total misclassifi

Keywords