Comparison of Fuzzy Rule Based Classi cation with NeuralNetwork Approaches For Medical Diagnosis

Several methods of fuzzy rule based classiication are applied to medical data. Features from patient data, collected in a clinic, are pre-processed before being fed into fuzzy neural networks, where fuzzy rule based classiication systems are generated. Additionally, results obtained from feed-forward architectures such as standard-backpropagation networks, radial basis function nets (RBF) and Dynamic Vector Quantization (DVQ) are compared with the generated fuzzy classiier systems. The detection of certain phenomena in EEGs, so-called graphoelements, is the major problem handled in this work. The traditional way of reading pages of EEG diagrams by the trained medical practitioners can be eased by this method of automation. Results show the relative performances of the compared networks and possible applications to other medical data. The approaches, sketched here, particularly the classiier and the concept of membership function generation, are not dedicated to EEG classiication, but may as well be applied to any set of features in patient data that can be transformed into a fuzzy representation.