EdgeConv-Based Spatial Difference Extraction of Plantar Pressure Improves Mediolateral Ground Reaction Force Estimation During Walking

Open Access
Article
Conference Proceedings
Authors: Hideyuki Nagashio, Yusuke Osawa, Kazunori Kaede, Keiichi Watanuki
Abstract

Falls and fractures are major concerns in super-aged societies, highlighting the need for gait assessment in daily living environments. Wearable footwear devices equipped with plantar pressure sensors and inertial measurement units (IMUs) enable remote gait monitoring without laboratory-based equipment; however, they cannot directly measure three-dimensional ground reaction forces (3D GRFs), and estimating the mediolateral component (Fx), which is related to balance control, remains challenging. This paper proposes a deep learning model that integrates Edge Convolution (EdgeConv), a graph neural network layer, to extract spatial features from plantar pressure data and improve Fx estimation. Gait experiments were conducted with 12 healthy participants walking on an instrumented treadmill, during which 3D GRFs and wearable sensor data from eight plantar pressure sensors and a six-axis IMU were synchronously recorded. The proposed model combines EdgeConv for spatial feature extraction with a Transformer for temporal feature learning and was evaluated using subject-independent six-fold group cross-validation. For Fx estimation, the proposed model achieved an NRMSE of 8.79 ± 1.26% and an R² of 0.76 ± 0.09, compared with 9.30 ± 1.52% and 0.73 ± 0.09 for the Transformer and 9.47 ± 1.77% and 0.71 ± 0.13 for the GCN. These results indicate that learning local spatial features with EdgeConv enhances mediolateral GRF estimation from wearable footwear sensor data.

Keywords: 3D Ground Reaction Forces (3D GRFs), EdgeConv, Walking Analysis, Plantar Pressure, IMU Sensor

DOI: 10.54941/ahfe1008308

Cite this paper
Downloads
0
Visits
1
Download PDF

More from this volume

← Stakeholder requirements for quality-in-useIncorporating User Research Findings into a Model-Based Enterprise Architecture to Protect the Ocean →
View all articles in Human Factors in Design, Engineering, and Computing →