Nonparametric walking model based on relationship between plantar insole sensor signal time-spatial features

Abstract

This work contrasts traditional parametric walking models, which handle simple gait well but fail on nonlinear or disease-affected patterns, with a Non-Parametric Walking Model (NPWM) built from plantar insole time–spatial features. The Neurological Disease Detection Feature Mining Method (NDFMM) identifies goal-oriented walking patterns through sorted-metrics–based selection. Combining NPWM and NDFMM provides a robust approach for modeling complex gait dynamics and enhancing disease-related classification.