Discrete Versus Continuous Mapping of Facial Electromyography for Human-Machine Interface Control: Performance and...

Area of Science:

• Biomedical Engineering
• Rehabilitation Technology
• Human-Computer Interaction

Background:

• Individuals with high spinal cord injuries often face significant challenges with traditional hand-operated computer input devices.
• Developing alternative control methods is crucial for restoring digital independence and improving quality of life.

Purpose of the Study:

• To compare the efficacy of two surface electromyography (sEMG)-based control systems for an onscreen keyboard.
• To evaluate the impact of training and system type on typing performance.

Main Methods:

• Two sEMG systems (discrete and continuous) were developed, utilizing facial gestures mapped to cursor commands.
• Participants controlled an onscreen keyboard using sEMG data from facial muscles.
• Training involved four daily sessions on one system, followed by a crossover session on the other.

Main Results:

• Both systems achieved high information transfer rates (ITRs), indicating effective control.
• ITRs increased significantly with training, from 62.1 bits/min (Session 1) to 105.1 bits/min (Session 4).
• The continuous sEMG system yielded significantly higher ITRs compared to the discrete system.

Conclusions:

• sEMG-controlled onscreen keyboards represent a viable alternative input modality for individuals with severe motor impairments.
• Continuous control algorithms show greater potential for enhanced typing performance.
• Further development of these systems could provide significant benefits for users with diverse motor disabilities.