Structure and Evolving Fuzzy Models for Prosthetic Hand Myoelectric-Based Control Systems

This paper suggests a structure for prosthetic hand myoelectric-based control systems and a set of evolving Takagi-Sugeno-Kang (TSK) fuzzy models to characterize mathematically the finger dynamics of the human hand for the myoelectric control of prosthetic hands. The fuzzy models represent the reference models in myoelectric-based control systems, the model outputs are the flexion percentages that correspond to the midcarpal joint angles, and the model inputs are the myoelectric signals obtained from eight myoelectric sensors. Different numbers of additional model inputs obtained from past inputs and/or outputs are considered. The structure and parameters of the fuzzy models are evolved by an incremental online identification algorithm (IOIA). The evolving TSK fuzzy models for one finger are tested against the experimental data, and a comparison with similar TSK fuzzy models evolved by another IOIA and a neural network model with similar number of parameters is included.