A hybrid intelligent system and its application to medical diagnosis

Scope and method of study. A novel hybrid intelligent system (HIS) that provides a unified integration of numerical and linguistic knowledge representations is proposed. The proposed HIS is a hierarchical integration of an incremental learning fuzzy neural network (ILFN) and a linguistic model, i.e., fuzzy expert system (FES), optimized via the genetic algorithm (GA). The ILFN is a self-organizing network with the capability of fast, one-pass, online, and incremental learning. The linguistic model is constructed based on knowledge embedded in the trained ILFN or provided by the domain expert. The knowledge captured from the low-level ILFN can be mapped to the higher-level linguistic model and vice versa. The GA is applied to optimize the linguistic model to maintain high accuracy and comprehensibility. Findings and conclusions. The resulting HIS is capable of dealing with low-level numerical computation and higher-level linguistic computation. After the system is successfully constructed, it can incrementally learn new information in both numerical and linguistic forms. To evaluate the system's performance, several data sets namely the Iris data set, the Wisconsin breast cancer data set, and the three medical data sets (Breast Cancer Data, Lymphograph Domain, and Primary Tumor Domain) from the Institute of Oncology, University Medical Center, Ljubliana, Yugoslavia, were used. The simulation results have shown that the proposed HIS achieved classification accuracy better than the individual standalone systems. The comparison results based on performance classification show that the linguistic rules extracted are competitive with some well-known approaches in literature.