Abstract
Entropy methods including approximate entropy (ApEn), sample entropy (SampEn) and multiscale entropy (MSE) have recently been applied to measure the complexity of finite length time series for classification of diseases. In order to effectively use these entropy methods, parameters such as m, r, and scale factor (in MSE) are to be determined. So far, there have been no general rules to select these parameters as they depend on particular problems. In this paper, we introduce a genetic algorithm (GA) based method for optimal selection of these parameters in a sense that the entropic difference between healthy and pathologic groups are maximized.