[Multi-objective optimization for fuzzy controller in neuro-muscular rehabilitation]

Area of Science:

• Computational intelligence
• Control systems engineering
• Biomedical engineering

Context:

• Multi-objective optimization problems (MOOPs) are common in engineering.
• Genetic algorithms (GAs) are effective for non-derivative, ill-posed MOOPs.
• E-health applications in neuromuscular rehabilitation require efficient control systems.

Purpose:

• To apply multi-objective optimization to fuzzy controller design.
• To develop a minimal fuzzy architecture for resource-constrained micro-controllers.
• To achieve optimal performance in electromyography-based rehabilitation systems.

Summary:

• This research utilizes multi-objective optimization with genetic algorithms to design fuzzy controllers for e-health applications.
• The focus is on creating a compact fuzzy logic system suitable for micro-controller deployment in neuromuscular rehabilitation using electromyography (EMG).
• The optimized fuzzy architecture aims to balance competing objectives within limited hardware capabilities.

Impact:

• Enables efficient and effective e-health solutions for neuromuscular rehabilitation.
• Demonstrates the feasibility of advanced control strategies on embedded systems.
• Advances the integration of intelligent control in biomedical devices.