Development of paraplegic quadriceps muscle model using ANN and ANFIS

This paper presents the development of Quadriceps muscle model by using Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) based on Functional Electrical Stimulation (FES). The impacts of the output torque with different stimulation parameters (frequency, pulse width and sampling time) are investigated. These parameters will be used to develop the paraplegic muscle models. Muscle models developed are validated with the clinical data to evaluate the accuracy of the output torque predicted compare to the actual paraplegic muscle torque. From the study, ANN is found to be the most accurate model compare to ANFIS with the value of mean squared error of 0.3758. Both developed models in this study can be used in a various control strategies to control FES parameters during rehabilitation proses using FES.