Related Experiment Video
Updated: Apr 14, 2026
04:06
Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
Published on: January 12, 2024
1.2K
Muscles data compression in body sensor network using the principal component analysis in wavelet domain.
Elmira Yekani Khoei1, Reza Hassannejad2, Behzad Mozaffari Tazehkand3
1Faculty of Computer, College of Engineering, East Azerbaijan Science and Research Branch, Islamic Azad University, Tabriz, Iran.
Bioimpacts : BI
|April 23, 2015
Summary
This study introduces a novel compression method for body sensor networks, enhancing data coherence and reducing noise for better physiological monitoring. The new technique improves compression rates compared to existing methods.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Data Compression
Background:
- Body sensor networks (BSNs) are crucial for remote physiological monitoring, aiding in early disease detection.
- BSNs utilize small sensors but face limitations in computational power and energy efficiency.
Purpose of the Study:
- To develop an advanced data compression technique for BSNs.
- To improve data coherence and compression rates while maintaining data quality.
Main Methods:
- A new compression method combining principal component analysis (PCA) and wavelet transform was developed.
- PCA enhances data similarity and compression ratio; wavelet transform decomposes data for selective restoration.
- Noise is omitted during data restoration, improving signal quality and enabling effective compression.
Main Results:
- The proposed method demonstrated compression ratios ranging from 0.6009 to 0.8898 across twelve patients.
- These results were compared against the Tseng algorithm, a previous method, which yielded compression ratios from 0.8046 to 0.9732.
Conclusions:
- The proposed compression method shows effectiveness in improving compression rates.
- The method's exactness is supported by comparisons of compression rates and prediction errors with existing results.
