Sensor-based Gait Parameter Extraction with Deep Convolutional Neural Networks

Abstract

Measurement of stride-related, biomechanical parameters is the common rationale for objective gait impairment scoring. State-of-the-art double integration approaches to extract these parameters from inertial sensor data are, however, limited in their clinical applicability due to the underlying assumptions. To overcome this, we present a method to translate the abstract information provided by wearable sensors to context-related expert features based on deep convolutional neural networks. Regarding mobile gait analysis, this enables integration-free and data-driven extraction of a set of 8 spatio-temporal stride parameters. To this end, two modelling approaches are compared: A combined network estimating all parameters of interest and an ensemble approach that spawns less complex networks for each parameter individually. The ensemble approach is outperforming the combined modelling in the current application. On a clinically relevant and publicly available benchmark dataset, we estimate stride length, width and medio-lateral change in foot angle up to $-0.15\pm 6.09$ cm, $-0.09\pm 4.22$ cm and $0.13\pm 3.78^{\circ }$ respectively. Stride, swing and stance time as well as heel and toe contact times are estimated up to $\pm 0.07$, $\pm 0.05$, $\pm 0.07$, $\pm 0.07$ and $\pm 0.12$ s respectively. This is comparable to and in parts outperforming or defining state-of-the-art. Our results further indicate that the proposed change in methodology could substitute assumption-driven double-integration methods and enable mobile assessment of spatio-temporal stride parameters in clinically critical situations as e.g. in the case of spastic gait impairments.

in IEEE Journal of Biomedical and Health Informatics (2016)

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Deep Residual Learning for Image Recognition
• Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables
• Stride Length Estimation with Deep Learning

Cited by in corpus (12)

• Deep Learning for Sensor-based Activity Recognition: A Survey
• Vision-Based Assessment of Parkinsonism and Levodopa-Induced Dyskinesia with Deep Learning Pose Estimation
• Automatic Classification of Functional Gait Disorders
• TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors
• IMU Based Deep Stride Length Estimation With Self-Supervised Learning
• Deep Learning Techniques for Improving Digital Gait Segmentation
• Sensor Fusion for Predictive Control of Human-Prosthesis-Environment Dynamics in Assistive Walking: A Survey
• Real-Time Wearable Gait Phase Segmentation For Running And Walking
• Deep Gait Tracking With Inertial Measurement Unit
• Classification of anomalous gait using Machine Learning techniques and embedded sensors
• Octave Mix: Data augmentation using frequency decomposition for activity recognition
• Pedestrian Tracking with Gated Recurrent Units and Attention Mechanisms