A fuzzy logic model for hand posture control using human cortical activity recorded by micro-ECog electrodes.

Area of Science:

• Neuroscience
• Biomedical Engineering
• Artificial Intelligence

Background:

• Decoding neural signals for prosthetic control is a growing field.
• Electro-corticography (ECoG) offers a high-resolution window into brain activity.
• Fuzzy logic provides a robust framework for handling imprecise data.

Purpose of the Study:

• To develop and evaluate a fuzzy logic model for decoding hand posture from ECoG signals.
• To assess the accuracy of the model in distinguishing between open and closed hand postures.
• To enable real-time control of a virtual hand based on decoded neural activity.

Main Methods:

• Recorded ECoG signals from a single subject during reach and grasp tasks.
• Selected optimal electrodes based on task-related activity.
• Extracted power spectral densities from neural signals.
• Fed signal features into a fuzzy logic model for posture decoding.
• Validated decoded postures against data glove recordings.

Main Results:

• The fuzzy logic model accurately decoded open or closed hand postures with 80% accuracy.
• Acceleration-based decoding of hand postures showed superior performance compared to velocity-based decoding.
• The model was successfully implemented in MATLAB/SIMULINK for virtual hand control.

Conclusions:

• Fuzzy logic is a viable approach for decoding hand posture from ECoG signals.
• The developed model demonstrates potential for advanced brain-computer interfaces.
• This technology could lead to more intuitive control of prosthetic limbs and virtual environments.