Application of least square method for muscular strength estimation in hand motion recognition using surface EMG

Area of Science:

• Biomedical Engineering
• Rehabilitation Engineering
• Signal Processing

Background:

• Surface electromyogram (SEMG) is a crucial biological signal reflecting human motion intention, widely used in control systems.
• Current SEMG systems primarily focus on recognition accuracy, often neglecting the estimation of muscular strength.
• Accurate muscular strength estimation is vital for effective control of SEMG-based systems.

Purpose of the Study:

• To develop a novel method for estimating muscular strength using the least squares method.
• To enhance hand motion recognition in SEMG systems by incorporating muscular strength estimation.
• To establish a relationship between SEMG signals and grasp force for improved system control.

Main Methods:

• Application of the least squares method to model the relationship between SEMG and grasp force.
• Utilizing grasp force as a key index for evaluating muscular strength.
• Employing the Monte Carlo method to determine optimal SEMG measurement locations, considering individual differences.

Main Results:

• Successfully developed a method to estimate muscular strength from SEMG signals.
• Demonstrated the potential to reflect measured muscle power in controlled objects.
• Established a quantifiable link between SEMG variations and grasp force.

Conclusions:

• The least squares method provides an effective approach for muscular strength estimation in SEMG-based systems.
• Integrating muscular strength estimation improves the control capabilities and accuracy of hand motion recognition.
• This method offers a pathway to more intuitive and responsive human-machine interfaces.