Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Detecting Heel Strike and toe off Events Using Kinematic Methods and LSTM Models

Longbin Zhang, Tsung-Lin Wu, Ananda Sidarta, Xiaoyue Yan, Prayook Jatesiktat, Kailun Yang, Wei Tech Ang

TL;DR

This study systematically compares seven kinematics-based gait event detection methods with an LSTM for identifying heel strike and toe-off events using a large normative dataset of 4363 gait cycles from 588 healthy adults. Ground truth HS/TO were derived from force plate data, enabling precise temporal-error evaluation against both traditional kinematic cues and a data-driven LSTM model. Results show that the Zeni et al. kinematic method yields the smallest HS error among kin methods, while the LSTM achieves comparable accuracy without systematic bias, highlighting the viability of deep learning approaches. The work underscores the potential for improved gait-event detection in rehabilitation and exoskeleton control, while emphasizing the need for validation in pathological populations and across diverse data collection settings.

Abstract

Accurate gait event detection is crucial for gait analysis, rehabilitation, and assistive technology, particularly in exoskeleton control, where precise identification of stance and swing phases is essential. This study evaluated the performance of seven kinematics-based methods and a Long Short-Term Memory (LSTM) model for detecting heel strike and toe-off events across 4363 gait cycles from 588 able-bodied subjects. The results indicated that while the Zeni et al. method achieved the highest accuracy among kinematics-based approaches, other methods exhibited systematic biases or required dataset-specific tuning. The LSTM model performed comparably to Zeni et al., providing a data-driven alternative without systematic bias. These findings highlight the potential of deep learning-based approaches for gait event detection while emphasizing the need for further validation in clinical populations and across diverse gait conditions. Future research will explore the generalizability of these methods in pathological populations, such as individuals with post-stroke conditions and knee osteoarthritis, as well as their robustness across varied gait conditions and data collection settings to enhance their applicability in rehabilitation and exoskeleton control.

Detecting Heel Strike and toe off Events Using Kinematic Methods and LSTM Models

TL;DR

This study systematically compares seven kinematics-based gait event detection methods with an LSTM for identifying heel strike and toe-off events using a large normative dataset of 4363 gait cycles from 588 healthy adults. Ground truth HS/TO were derived from force plate data, enabling precise temporal-error evaluation against both traditional kinematic cues and a data-driven LSTM model. Results show that the Zeni et al. kinematic method yields the smallest HS error among kin methods, while the LSTM achieves comparable accuracy without systematic bias, highlighting the viability of deep learning approaches. The work underscores the potential for improved gait-event detection in rehabilitation and exoskeleton control, while emphasizing the need for validation in pathological populations and across diverse data collection settings.

Abstract

Accurate gait event detection is crucial for gait analysis, rehabilitation, and assistive technology, particularly in exoskeleton control, where precise identification of stance and swing phases is essential. This study evaluated the performance of seven kinematics-based methods and a Long Short-Term Memory (LSTM) model for detecting heel strike and toe-off events across 4363 gait cycles from 588 able-bodied subjects. The results indicated that while the Zeni et al. method achieved the highest accuracy among kinematics-based approaches, other methods exhibited systematic biases or required dataset-specific tuning. The LSTM model performed comparably to Zeni et al., providing a data-driven alternative without systematic bias. These findings highlight the potential of deep learning-based approaches for gait event detection while emphasizing the need for further validation in clinical populations and across diverse gait conditions. Future research will explore the generalizability of these methods in pathological populations, such as individuals with post-stroke conditions and knee osteoarthritis, as well as their robustness across varied gait conditions and data collection settings to enhance their applicability in rehabilitation and exoskeleton control.

Paper Structure

This paper contains 8 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Experimental Setup
  4. Gait Event Identification Models
  5. Evaluation Protocol
  6. Results
  7. Discussion
  8. Conclusion

Figures (3)

  • Figure 1: Schematic diagram of gait event identification using kinematics-based or machine learning models. The inputs for these models consist of key marker trajectories from the toe, heel, or pelvis, acquired and post-processed using a 3D motion capture system.
  • Figure 2: The boxplot of prediction errors (time differences) between the measured and calculated heel strike (left) and toe off (right) events using various kinematics-based methods and the LSTM model.
  • Figure 3: The histogram of time differences between the measured and calculated heel strike (left) and toe off (right) events using various kinematics-based methods and the LSTM model.