In this paper, we present a novel approach to model and classify gait patterns based on internal models. An internal model consists of two sets of differential equations and a neural network in between. It can effectively describe dynamic movement primitives (DMP), hence is able to model the temporal-spatial gait patterns. An interesting feature of the internal model is, the nonlinear map generated by the neural network can also serve the purpose for gait pattern classification. In this work we use a single hidden layer feedforward network (SLFN), and show that the characteristics of gait patterns can be captured via the output layer weights. The experiment results based on EMGs of gait patterns at five different walking speeds are used to validate the internal model approach.
Internal model approach for gait modeling and classification. Publishing Authors By Initials
