A fuzzy muscle force estimator for use within an intelligent expert system

Traditionally, evaluations involving three-dimensional (3D) biomechanical analysis have produced prohibitive quantities of data which very few clinicians have been trained to interpret. What is needed is a clinician-assistant system to aid clinicians in more effective synthesis of modeling tools with their clinical experience. The first step in realizing this system-and the focus of this paper-is the development of a fuzzy EMG-to-muscle force estimator that captures dynamic muscle properties while providing robustness to partial data. The resulting force estimate is more accurate than simply smoothing EMG, and the robustness is an improvement over a dynamical nonlinear Hill muscle model