Classification of incomplete feature vectors by radial basis function networks

The paper describes the use of radial basis function neural networks with Gaussian basis functions to classify incomplete feature vectors. The method uses the fact that any marginal distribution of a Gaussian distribution can be determined from the mean vector and covariance matrix of the joint distribution.

Associations of the mechanical, anthropometric and gait contributors to the knee adduction moment during paediatric gait

The knee adduction moment (KAM) during gait has been proposed as an indirect measure of dynamic knee joint loading and has been reported to be higher in obese children [1, 2]. The KAM is primarily calculated from the resultant ground reaction force (GRF) and the lever arm length, both of which can be manipulated through weight-loss or medical interventions [1]. However, there is little data on the relationships between the mechanical, anthropometric and gait contributors to the KAM during paediatric gait. The objectives of the study were to examine the associations with the first (1st) and second (2nd) peak KAM (pKAM) and: (1) centre of pressure (CoP), KAM lever arm length, vertical and mediolateral ground reaction forces (GRF) and, (2) fat mass, height, step width, foot rotation, knee rotation and walking velocity.