Characterization of Functions Using Artificial Intelligence to Reproduce Complex Systems Behavior: Takagi Sugeno Kang Order 2 to Reproduce Cardiac PQRST Complex

Abstract

In the field of signal processing, for forecasting purposes, the characterization of functions is a key factor to be faced. In most of the cases, the characterization can be achieved by applying least square estimation (LSE) to polynomial functions; however, it is not fully in all cases. To contribute in this field, this article proposes a variant of artificial intelligence based on fuzzy characterization patterns initialized by Lagrange interpolators and trained with neuro-adaptive system. The aim is to minimize a cost function based on the absolute value between samples and their prediction. The proposal is applied to the characterization of cardiac PQRST complex as case study. The results show a satisfactory performance providing an error of around 1.42% compared to the normalized PQRST complex signal.