Related Experiment Video
Updated: Dec 23, 2025
08:05
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
11.1K
Hardware/Software Co-design of Fractal Features based Fall Detection System
Ahsen Tahir1,2, Gordon Morison1, Dawn A Skelton3
1School of Computing, Engineering and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UK.
Sensors (Basel, Switzerland)
|April 25, 2020
Summary
This study introduces a novel wearable Fall Detection System (FDS) using fractal dynamics in accelerometer signals. The system significantly improves fall detection accuracy and energy efficiency for older adults.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Wearable Technology
Background:
- Falls are a major cause of mortality and morbidity in older adults.
- Timely medical intervention is crucial, and Fall Detection Systems (FDS) can reduce mortality rates.
- Existing FDS may lack accuracy or energy efficiency in wearable applications.
Purpose of the Study:
- To propose and evaluate a novel wearable Fall Detection System (FDS).
- To exploit fractal dynamics of accelerometer signals for accurate fall classification.
- To design an energy-efficient hardware/software co-design for real-time fall detection.
Main Methods:
- Developed a wearable sensor FDS utilizing fractal dynamics and multi-level wavelet transform.
- Implemented a hardware feature accelerator on a Zynq System on Chip for fractal feature computation.
- Employed a hardware/software co-design with Linear Discriminant Analysis on an embedded ARM core.
Main Results:
- Achieved 99.38% fall detection accuracy.
- Demonstrated a 7.3x speed-up and 6.53x improvement in power consumption compared to software-only execution.
- Reported a 47.6x overall performance per Watt advantage with low resource utilization (28.67%).
Conclusions:
- Fractal dynamics are effective discriminators for fall detection from accelerometer data.
- The proposed hardware/software co-design FDS offers high accuracy and significant energy efficiency.
- This novel system holds promise for improving safety and independence in older adults.
