Multi-modal Prosthesis Control using sEMG, FMG and IMU Sensors.

Area of Science:

• Biomedical Engineering
• Rehabilitation Technology
• Human-Computer Interaction

Background:

• Advanced prosthetic control is crucial for restoring daily living activities.
• Non-invasive sensing modalities offer potential for intuitive prosthetic interfaces.
• Integrating multiple sensor types can enhance signal robustness and accuracy.

Purpose of the Study:

• To develop and evaluate a novel multi-modal wearable device for simultaneous data collection.
• To assess the efficacy of combining force myography (FMG), surface electromyography (sEMG), and inertial measurement unit (IMU) sensors for gesture recognition.
• To improve the accuracy and consistency of prosthetic control through enhanced intent prediction.

Main Methods:

• A wearable armband was designed integrating FMG, sEMG, and IMU sensors.
• Subjects performed activities of daily living (ADL) gestures while data was collected.
• An established machine learning algorithm was employed to classify sensor signals and predict user intent.

Main Results:

• The combined use of FMG, sEMG, and IMU sensors yielded statistically significant improvements in gesture classification accuracy.
• The three-modality approach demonstrated superior performance compared to most other sensor combinations.
• Consistent and accurate prediction of user gestures was achieved, indicating high reliability.

Conclusions:

• A novel multi-modal sensing device significantly enhances the accuracy of gesture recognition for prosthetic control.
• Integrating FMG, sEMG, and IMU offers a robust solution for improving upper-limb prosthetic functionality.
• This technology holds clinical relevance for advancing prosthetic device usability and user independence.