Related Experiment Video
Updated: Mar 29, 2026
07:24
Home-Based Monitor for Gait and Activity Analysis
Published on: August 8, 2019
7.4K
A Wearable Multi-Modal Measurement System with Self-Developed IMUs and Plantar Pressure Sensors for Real-Time Gait
Xiuyu Li1,2, Yunong Gao1, Guanzhong Chen2
1Electrical Measurement Technology and Intelligent Control Institute, School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150080, China.
Micromachines
|March 28, 2026
Summary
This study introduces a novel wearable system combining inertial and plantar pressure sensors for advanced gait recognition. The innovative approach significantly improves accuracy in recognizing static, transitional, and dynamic human gaits.
Area of Science:
- Biomedical Engineering
- Human-Computer Interaction
- Sensor Technology
Background:
- Existing wearable gait recognition systems struggle with accuracy in static postures and recognizing transitional movements.
- Limitations include sensor drift and challenges in capturing complex human motion dynamics.
Purpose of the Study:
- To develop a robust wearable gait recognition system overcoming current limitations.
- To enhance accuracy for static, transitional, and dynamic human gaits using multi-modal sensor fusion.
Main Methods:
- A low-power wearable device with four Microelectromechanical Systems (MEMS) Inertial Measurement Units (IMUs) and two flexible plantar pressure sensors was designed.
- A two-stage hierarchical algorithm was developed, utilizing plantar pressure for posture classification and a combination of Support Vector Machine (SVM), Finite State Machine (FSM), and ensemble learning for gait recognition.
Main Results:
- The proposed system achieved a comprehensive gait recognition accuracy of 96.17% using Leave-One-Out Cross-Validation.
- Perfect 100% accuracy was recorded for standing recognition, and 97% accuracy for sit-to-stand transitions.
Conclusions:
- Multi-modal sensor fusion significantly enhances the robustness and generalization of wearable gait recognition systems.
- The developed system offers a promising solution for accurate and reliable human gait analysis in various applications.
