A novel auto regression and fuzzy-neural combination method to identify cardiovascular dynamics

In this paper cardiovascular dynamics, which refers to the dynamic relationship among the heart rate (HR), arterial blood pressure (ABP) and instantaneous lung volume (ILV), is identified through a novel combination approach that consists of a set of linear auto-regression (AR) equations and nonlinear fuzzy-neural inference. Based on linear assumption of cardiovascular system, auto-regressive and moving average method (ARMA) has been popular approaches to identify the complex cardio-system in recent years. Fuzzy set theory is very suitable to systems with uncertainties such as the cardiovascular dynamic system with expert knowledge. Fuzzy- Neural inference paradigm imports the auto-learning property into fuzzy logic engine, therefore extracts some knowledge from data automatically. An effective hybrid approach, which has parallel modular structure of AR and Fuzzy-neural inference, becomes feasible IO interpret physiologically linear component of heart function and nonlinear nervous regulation component respectively. Details of proposed combination method as well as subjects' study results are presented in this paper.