Back to search

Georgia Institute of Technology

Gait signatures: data-driven discovery of individual-specific neuromechanical dynamics

Abstract

dc:description.abstract

Human gait is an important aspect of mobility that impacts the ability to perform everyday activities, safety and quality of life. Changes in gait patterns can have clinical implications, indicating risks for conditions such as osteoarthritis or changes in disease progression. Standard gait evaluation methods often rely on visual observation or subjective selection of discrete gait variables, overlooking continuous data and complex inter-limb and inter-joint spatiotemporal dependencies that underlie gait and impairment. The lack of reliable, quantitative metrics for tracking and assessing individual-specific gait differences can impact rehabilitation prescriptions, and the development of tailored rehabilitation solutions. This thesis introduces a novel, data-driven approach to model the dynamics of human gait, effectively capturing the complex spatiotemporal dependencies between individuals’ joint angles, arising from joint neural and biomechanical constraints (Aim 1). Individual-specific representations of gait dynamics, termed “gait signatures”, provide a holistic method for identifying and quantifying gait differences in both health and disease. I demonstrate that gait signatures in able-bodied individuals remain consistent across a wide range of walking speeds, with speed-induced changes being both predictable and linear (Aim 2). Additionally, I show that gait signatures can track and quantify clinically meaningful changes in stroke survivors’ gait dynamics through two longitudinal gait interventions (Fast and Fast Functional Electrical Stimulation) (Aim 3). Together, these findings underscore the utility of gait signatures as a quantitative tool for enhancing gait analysis in both sports and clinical settings, facilitating the development of personalized rehabilitation treatment plans.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Biomedical Engineering (Joint GT/Emory Department)
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Winner, Taniel S.
Advisor dc:contributor.advisor
  • Ting, Lena H.
Committee members dc:contributor.committeemember
  • Berman, Gordon
  • Kesar, Trisha
  • Chang, Young-Hui
  • Wheaton, Lewis

Subjects

dc:subject × 8

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/75674

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Winner, Taniel S.. Gait signatures: data-driven discovery of individual-specific neuromechanical dynamics. Doctoral thesis, Georgia Institute of Technology, 2024. https://hdl.handle.net/1853/75674