Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reliable Vertical Ground Reaction Force Estimation with Smart Insole During Walking

Femi Olugbon, Nozhan Ghoreishi, Ming-Chun Huang, Wenyao Xu, Diliang Chen

Abstract

The vertical ground reaction force (vGRF) and its characteristic weight acceptance and push-off peaks measured during walking are important for gait and biomechanical analysis. Current wearable vGRF estimation methods suffer from drifting errors or low generalization performances, limiting their practical application. This paper proposes a novel method for reliably estimating vGRF and its characteristic peaks using data collected from the smart insole, including inertial measurement unit data and the newly introduced center of the pressed sensor data. These data were fused with machine learning algorithms including artificial neural networks, random forest regression, and bi-directional long-short-term memory. The proposed method outperformed the state-of-the-art methods with the root mean squared error, normalized root mean squared error, and correlation coefficient of 0.024 body weight (BW), 1.79% BW, and 0.997 in intra-participant testing, and 0.044 BW, 3.22% BW, and 0.991 in inter-participant testing, respectively. The difference between the reference and estimated weight acceptance and push-off peak values are 0.022 BW and 0.017 BW with a delay of 1.4% and 1.8% of the gait cycle for the intra-participant testing and 0.044 BW and 0.025 BW with a delay of 1.5% and 2.3% of the gait cycle for the inter-participant testing. The results indicate that the proposed vGRF estimation method has the potential to achieve accurate vGRF measurement during walking in free living environments.

Reliable Vertical Ground Reaction Force Estimation with Smart Insole During Walking

Abstract

The vertical ground reaction force (vGRF) and its characteristic weight acceptance and push-off peaks measured during walking are important for gait and biomechanical analysis. Current wearable vGRF estimation methods suffer from drifting errors or low generalization performances, limiting their practical application. This paper proposes a novel method for reliably estimating vGRF and its characteristic peaks using data collected from the smart insole, including inertial measurement unit data and the newly introduced center of the pressed sensor data. These data were fused with machine learning algorithms including artificial neural networks, random forest regression, and bi-directional long-short-term memory. The proposed method outperformed the state-of-the-art methods with the root mean squared error, normalized root mean squared error, and correlation coefficient of 0.024 body weight (BW), 1.79% BW, and 0.997 in intra-participant testing, and 0.044 BW, 3.22% BW, and 0.991 in inter-participant testing, respectively. The difference between the reference and estimated weight acceptance and push-off peak values are 0.022 BW and 0.017 BW with a delay of 1.4% and 1.8% of the gait cycle for the intra-participant testing and 0.044 BW and 0.025 BW with a delay of 1.5% and 2.3% of the gait cycle for the inter-participant testing. The results indicate that the proposed vGRF estimation method has the potential to achieve accurate vGRF measurement during walking in free living environments.
Paper Structure (21 sections, 3 equations, 4 figures, 6 tables)

This paper contains 21 sections, 3 equations, 4 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Direct Measurement Methods of vGRF
  4. Traditional Measurement Methods
  5. Wearable Sensor-Based Measurement Methods
  6. Indirect Estimation Methods of vGRF
  7. Human Biomechanical Methods for vGRF Estimation
  8. Machine Learning Approaches for vGRF Prediction
  9. Foot Center of Pressure for vGRF Estimation
  10. Materials and Methods
  11. Smart Insole System
  12. Center of the Pressed Sensor Measurement
  13. Data Processing
  14. Machine Learning Algorithms for vGRF Estimation
  15. Model Training and Testing
  16. ...and 6 more sections

Figures (4)

  • Figure 1: Overview of the hardware elements of the smart insole system. (a) 3D model of the smart insole with an insole-shaped pressure sensor array on the top, an IMU in the middle, and a flexible substrate on the bottom; (b) The printed circuit board integrates the microcontroller, Bluetooth module, and the connector to the IMU and pressure sensor array; (c) The pressure-sensing array with pressure sensors uniformly distributed on it; (d) Assembled shoes with the smart insole system.
  • Figure 2: An overview of the process for data collection, data processing, vGRF estimation.
  • Figure 3: The experiment setup. The participant wears a pair of smart insole and walks on a force-plate instrumented treadmill.
  • Figure 4: Epoch graphs of the measured and estimated vGRF for the inter-participant testing method at different walking speeds. The median value has been plotted with lines, while the values between the $\mathrm{2.5^{th}}$ and $\mathrm{97.5^{th}}$ percentiles are shaded.