A New Cost Function for Parameter Estimation of Chaotic Systems Using Return Maps as Fingerprints

摘要: Estimating parameters of a model system using observed chaotic scalar time series data is topic active interest. To estimate these requires suitable similarity indicator between the and systems. Many works have considered measure in domain, which has limitations because sensitive dependence on initial conditions. On other hand, there are features systems that not to conditions such as topology strange attractor. We used this feature propose new cost function for parameter estimation models, we show its efficacy several simple