Machine Learning-Driven Individualized Gait Rehabilitation: Classification, Prediction, and Mechanism Design

Abstract

This paper presents a machine learning-based approach toward designing individually targeted rehabilitation devices. This approach consists of a classification model for early detection of a disease, regression, and artificial neural networks (ANNs) models to predict the target rehabilitation gait for a specific individual, and finally a generative approach for the conditional synthesis of single degree-of-freedom linkage mechanisms for gait rehabilitation. Design of mechanisms for human–machine interaction involves numerous subjective criteria and constraints in addition to the motion task. This is particularly important for the rehabilitation devices, where the size, complexity, weight, cost, and ease of use are critical factors. In this paper, we present an end-to-end computational approach for developing a device for individualized gait rehabilitation using machine learning techniques focusing on gait classification, prediction, and specialized device design. These models generate a distribution of linkage mechanisms, which strongly correlate to the distribution of target path variations. This way of formulating the problem results in a large variety of solutions to which subjective criteria can be applied to yield practically useful design concepts that would otherwise not be possible using traditional synthesis methods.