In this document, I demonstrate that: 1) Linear basis functions cannot outperform nonlinear ones to represent hand kinematics 2) Nonlinear autoencoders outperform PCA on the dimensionality reduction of hand kinematics, 3) Nonlinear autoencoders outperform PCA in human gait representation and recurrent nonlinear autoencoders can seamlessly express the temporal dynamics, 4)...
Humans have a remarkable ability to walk on a variety of surfaces. Compliant, uneven, or even slippery surfaces present little challenge to most people, yet are hazardous to individuals with locomotor impairments and even to bipedal robotic systems designed to mimic what we understand about human locomotion. Our ability to...
Step length is a common measurement taken during gait analyses. It allows one to determine asymmetries between the two legs, compare differences between subjects, and even compare intra-subject differences for changing parameters. Yet there has been little investigation of step length specifically and how it is modulated during walking. This...
The role that spinal motion plays during ambulation is not clearly understood. Little in vivo regional spinal motion data exists in the literature with regard to walking and most gait models disregard the upper body altogether, or regard it as a single rigid structure. This study aims to increase understanding...