Optimized algorithm for muscular diseases recognition based on temporal parameters analysis and correlation coefficients

Abstract

In this paper, an optimized algorithm based on temporal parameters analysis and correlation coefficients is presented in order to perform muscular diseases recognition. Statistical information was measured of three classes signals (Healthy, Myopathy and Neuropathy conditions). The temporal parameters that were initially proposed (14) were optimized based on the correlation coefficients. Thus, only 9 parameters were selected for optimized the algorithm, and the time required for training and recognition is ≈ 0.2s and ≈ 4ms, respectively.