Human-in-the-loop Auditory Cueing Strategy for Gait Modification

TL;DR

This paper introduces an adaptive auditory cueing system that personalizes gait modification by learning individual responses, outperforming fixed cueing methods in a study with healthy participants.

Contribution

It presents a novel framework combining gait monitoring and Gaussian Process-based adaptive cueing to enhance gait modification effectiveness.

Findings

Adaptive cueing outperforms fixed and proportional methods in gait change effectiveness.

The response model accurately predicts individual gait responses to cues.

The approach demonstrates potential for personalized gait rehabilitation strategies.

Abstract

External feedback in the form of visual, auditory and tactile cues has been used to assist patients to overcome mobility challenges. However, these cues can become less effective over time. There is limited research on adapting cues to account for inter and intra-personal variations in cue responsiveness. We propose a cue-provision framework that consists of a gait performance monitoring algorithm and an adaptive cueing strategy to improve gait performance. The proposed approach learns a model of the person's response to cues using Gaussian Process regression. The model is then used within an on-line optimization algorithm to generate cues to improve gait performance. We conduct a study with healthy participants to evaluate the ability of the adaptive cueing strategy to influence human gait, and compare its effectiveness to two other cueing approaches: the standard fixed cue approach and a proportional cue approach. The results show that adaptive cueing is more effective in changing the person's gait state once the response model is learned compared to the other methods.