Hybrid Neuro-Fuzzy Systems: Heterogeneous and Homogeneous Structures

This paper describes the design of hybrid neuro-fuzzy systems with heterogeneous and homogeneous structures. The system with a heterogeneous structure is developed for diagnosing myocardial perfusion from cardiac images. In this model, the neural network and fuzzy system work as independent components. When a new case is presented to the diagnostic system, the trained neural network determines inputs to the fuzzy system. Then the fuzzy system using predefined fuzzy sets and fuzzy rules, maps the given inputs to an output, and thereby obtains the risk of a heart attack. The system with a homogeneous structure is developed for predicting an aircraftpsilas trajectory during its landing aboard an aircraft carrier. A database of landing trajectories of various aircraft flown by different pilots is used to train the system, RADAR numerical data provides real-time trajectories of landing aircraft and the system predicts an aircraftpsilas trajectory at two seconds in advance, based on the aircraftpsilas current position.