Related Experiment Video
Updated: Oct 10, 2025
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
827
Verification of Normalization Method to Improve Usability and Versatility among Users of Applications that Predict
Summary
This study introduces a new electromyography (EMG) signal normalization method, improving usability and user versatility for continuous classification tasks. The technique eliminates calibration time and enhances accuracy across different users compared to traditional dynamic contraction methods.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Human-Computer Interaction
Background:
- Electromyography (EMG) applications require high user versatility and usability.
- Current EMG normalization methods like dynamic contraction (DC) suffer from low usability due to repeated calibration and low versatility because of signal nonlinearity and user variability.
Purpose of the Study:
- To enhance usability and user versatility for continuous EMG classification tasks.
- To develop a novel EMG signal normalization method addressing the limitations of existing techniques.
Main Methods:
- Developed a new EMG signal normalization method incorporating sliding-window and z-score normalization techniques.
- Evaluated the proposed method against dynamic contraction (DC) for usability and classification accuracy.
Main Results:
- The proposed method significantly improves usability by eliminating the need for calibration time.
- Classification accuracy for a model trained with the user's own data was comparable to DC (57%).
- For models trained with data from other users, the proposed method achieved 53% accuracy, an 18% improvement over DC (35%), demonstrating enhanced user versatility.
Conclusions:
- The novel sliding-window and z-score based normalization method enhances both usability and user versatility in EMG applications.
- This approach offers a practical solution for continuous EMG classification tasks, such as in prosthetic hand control, by overcoming the limitations of traditional methods.
