MMG-based classification of muscle activity for prosthesis control.

Area of Science:

• Biomedical Engineering
• Rehabilitation Engineering
• Prosthetics and Orthotics

Background:

• Mechanomyography (MMG), or muscle sound, is proposed as a functional alternative to electromyography (EMG) for muscle activity measurement.
• Integrating MMG into soft silicone sockets for below-elbow prosthetics aims to enhance comfort and functionality.

Purpose of the Study:

• To develop and validate an integrated strategy combining data and sensor fusion algorithms for MMG-based muscle activity detection, estimation, and classification.
• To enable practical prosthetic control through a multisensor MMG array embedded in a soft socket.

Main Methods:

• A two-stage MMG multisensor fusion strategy was implemented: a detection stage for muscle contraction presence and a classification stage for contraction type and control output.
• The system utilized an MMG multisensor array embedded distally within a silicon soft socket.

Main Results:

• The integrated strategy successfully enabled MMG-based detection and classification of muscle activity.
• Tests with amputees demonstrated that the proposed MMG approach is functionally comparable to, and potentially exceeds, electromyography (EMG).

Conclusions:

• MMG-based sensor fusion provides a viable and effective method for controlling externally powered prostheses.
• This technology offers a functional advancement for below-elbow amputees, potentially improving prosthetic device performance and user experience.