Related Experiment Video
Updated: Aug 25, 2025
14:52
Computerized Dynamic Posturography for Postural Control Assessment in Patients with Intermittent Claudication
Published on: December 11, 2013
11.5K
A Comparison among Different Strategies to Detect Potential Unstable Behaviors in Postural Sway
Bruno Andò1, Salvatore Baglio1, Salvatore Graziani1
1Department of Electric Electronic and Information Engineering, DIEEI, University of Catania, 95125 Catania, Italy.
Sensors (Basel, Switzerland)
|October 14, 2022
Summary
This study compares fall detection methods for frail individuals using postural sway analysis. Neuro-Fuzzy systems, especially with Discrete Wavelet Transform, show superior robustness against noise compared to threshold algorithms.
Area of Science:
- Biomedical Engineering
- Gerontology
- Assistive Technology
Background:
- Assistive Technology is crucial for assessing daily living and safety in frail individuals.
- Fall detection and prevention are key concerns for the elderly and those with mobility issues.
Purpose of the Study:
- To compare different strategies for analyzing postural sway to detect unstable standing postures.
- To identify precursors of potential falls in frail individuals.
Main Methods:
- Three postural sway analysis approaches were evaluated: a threshold-based algorithm, a Neuro-Fuzzy inference system, and a Neuro-Fuzzy system using Discrete Wavelet Transform (DWT) features.
- Performance was assessed using accuracy and reliability metrics on a large dataset.
Main Results:
- All three strategies demonstrated valuable performance in distinguishing between stable and unstable postural status.
- Neuro-Fuzzy inference systems exhibited better robustness against noisy data than the threshold-based algorithm.
Conclusions:
- Neuro-Fuzzy inference systems offer a more reliable approach for fall risk assessment, particularly in the presence of data noise.
- Advanced signal processing techniques like DWT can enhance the performance of fall prediction systems.
