Wearable optomyography enables continuous neuroprosthetic control

Area of Science:

• Biomedical Engineering
• Human-Computer Interaction
• Wearable Technology

Background:

• Surface electromyography (sEMG) is used in wearable devices for human-machine interfaces but suffers from limitations like sensor instability and signal artifacts.
• Existing sEMG techniques present challenges in sensor fixation, signal cross-talk, and long-term stability, hindering reliable computer command translation.

Purpose of the Study:

• To introduce and evaluate optomyography (OMG) as a superior alternative to sEMG for wearable human-machine interfaces.
• To demonstrate the efficacy of an OMG wristband system for computer control tasks.

Main Methods:

• Developed a 50-channel optomyography (OMG) wristband system for capturing muscle activity.
• Utilized a compact, fully connected neural network for decoding OMG signals based on hand gesture data.
• Trained and tested the system with able-bodied participants and an individual with limb loss on computer mouse-like tasks.

Main Results:

• Participants successfully controlled computer functions, including target acquisition and playing Tetris, using the OMG system.
• Performance was evaluated using metrics like trajectory deviation and dwell time, showing improvements with training.
• The OMG system demonstrated potential for enhanced performance, accuracy, stability, and versatility compared to traditional methods.

Conclusions:

• Optomyography (OMG) presents a promising next-generation technology for wearable human-machine interfaces.
• The developed OMG system offers a stable and versatile solution, overcoming limitations of conventional sEMG techniques.
• OMG technology has the potential to significantly advance the capabilities of wearable devices for computer interaction.