It is well-known that wavelet analysis[5], as a powerful
technique that can provide both spectral and temporal
information simultaneously, has successfully been applied in
the biomedical signal processing for feature extraction[5,6]. In
the present study, for the sake of improving the generalization
performance ANN-based gait classifier, we addressed a novel
scheme of intelligent model for automatic recognition of gait
patterns. The wavelet transform technique was firstly used to
extract some good features from highly correlated timedependent
gait variables, and then the extracted gait features
are used to initiate the training set of ANN. In order to evaluate
the proposed model effectively, the kinematic gait data of 24
young and 24 elderly participants were acquired and analyzed.
In addition, we compared the proposed model with the
classification model based on traditional selection of gait
features