A radial basis function model of muscle stimulated with irregular inter-pulse intervals

Area of Science:

• Biomedical Engineering
• Computational Neuroscience
• Muscle Physiology

Background:

• Skeletal muscle can be engineered for cardiac assistance through controlled electrical stimulation.
• Traditional muscle models (e.g., A.V. Hill's) struggle with nonlinearities and time-varying muscle properties.
• Pathological changes and stimulation effects further complicate muscle system modeling.

Purpose of the Study:

• To explore the use of nonlinear artificial neural networks for modeling electrically stimulated muscle.
• To investigate the efficacy of Radial Basis Function (RBF) networks over Multi-Layer Perceptrons (MLPs) for this application.
• To model the complex response of rabbit skeletal muscle to irregular electrical stimulation.

Main Methods:

• Development of a muscle model using a Radial Basis Function (RBF) network.
• Application of supramaximal electrical stimulation to rabbit skeletal muscle at irregular inter-pulse intervals.
• Utilizing the RBF network to capture nonlinear and time-varying muscle dynamics.

Main Results:

• The RBF network successfully modeled the behavior of electrically stimulated rabbit muscle.
• The RBF approach demonstrated advantages in handling complex muscle responses compared to traditional models.
• Irregular stimulation patterns were effectively incorporated into the muscle model.

Conclusions:

• Radial Basis Function networks offer a viable and effective approach for modeling electrically stimulated muscle for artificial function.
• This modeling technique holds promise for designing controllers for skeletal muscle-based cardiac assistance.
• Artificial neural networks provide a powerful tool for overcoming limitations of traditional muscle models in complex physiological scenarios.