Related Experiment Video
Updated: Apr 29, 2026
Using Wavelet Entropy to Demonstrate how Mindfulness Practice Increases Coordination between Irregular Cerebral and Cardiac Activities
Published on: May 10, 2017
The analysis of surface EMG signals with the wavelet-based correlation dimension method
Gang Wang1, Yanyan Zhang1, Jue Wang1
1Key Laboratory of Biomedical Information Engineering of Ministry of Education, Institute of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, 28 Xianning West Road, Xi'an 710049, China.
This study introduces a novel wavelet-based method to analyze nonlinear surface electromyographic (SEMG) signals for prosthetic control. The new approach achieves 100% accuracy in classifying forearm movements, improving prosthetic system performance.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Neuroscience
Background:
- Improving prosthetic systems relies on accurate classification of surface electromyographic (SEMG) signals.
- Extracting effective features from nonlinear SEMG signals remains a significant challenge.
- Existing methods struggle to fully capture the complex dynamics of SEMG signals.
Purpose of the Study:
- To develop a robust method for extracting features from SEMG signals.
- To enhance the classification accuracy of forearm movements for prosthetic control.
- To investigate the nonlinear and time-frequency characteristics of SEMG signals.
Main Methods:
- Proposed a wavelet-based correlation dimension method combining nonlinear time series analysis and time-frequency domain techniques.
- Analyzed SEMG signals using wavelet transform and calculated correlation dimension for feature extraction.
- Utilized Gustafson-Kessel clustering classifier with extracted features to discriminate four forearm movements.
Main Results:
- The wavelet-based correlation dimension method effectively extracted features from SEMG signals.
- Achieved 100% classification accuracy for four types of forearm movements using two SEMG channels.
- Identified distinct clusters corresponding to different movements at the third resolution level.
Conclusions:
- The proposed approach offers significant insights into nonlinear and time-frequency features of SEMG signals.
- This method is highly suitable for classifying forearm movements in prosthetic applications.
- Demonstrated superior robustness and higher classification accuracy compared to existing methods.
