Deep Convolutional and LSTM Networks on Multi-Channel Time Series Data for Gait Phase Recognition.

David Kreuzer,Michael Munz

doi:10.3390/s21030789

Abstract

With an ageing society comes the increased prevalence of gait disorders. The restriction of mobility leads to a considerable reduction in the quality of life, because associated falls increase morbidity and mortality. Consideration of gait analysis data often alters surgical recommendations. For that reason, the early and systematic diagnostic treatment of gait disorders can spare a lot of suffering. As modern gait analysis systems are, in most cases, still very costly, many patients are not privileged enough to have access to comparable therapies. Low-cost systems such as inertial measurement units (IMUs) still pose major challenges, but offer possibilities for automatic real-time motion analysis. In this paper, we present a new approach to reliably detect human gait phases, using IMUs and machine learning methods. This approach should form the foundation of a new medical device to be used for gait analysis. A model is presented combining deep 2D-convolutional and LSTM networks to perform a classification task; it predicts the current gait phase with an accuracy of over 92% on an unseen subject, differentiating between five different phases. In the course of the paper, different approaches to optimize the performance of the model are presented and evaluated.

Highlights

Even though walking is the most basic method of locomotion, independence and self-determination are linked to it
Throughout this paper, a deep neural network model based on a combination of convolutional neural networks (CNNs)
Labels are generated highly individually, and one step is separated into five phases

Summary

Introduction

Even though walking is the most basic method of locomotion, independence and self-determination are linked to it. Often caused by occasional pain, injuries or surgeries in the past, can lead to serious damage in the lower limbs and back [1,2,3]. Detection of wrong movements can help to prevent worse conditions. Instead of fighting the symptoms, it can be more helpful to identify the underlying cause by analyzing the movement patterns. These patterns can be found and evaluated with the use of gait analysis methods. Gait analysis is primarily performed by visual experts’ valuation in real time or by using specialized measurement equipment. The use of supporting systems offers the advantage of more accurate and data-driven evaluations

Methods

Results

Discussion

Conclusion