Adaptive fuzzy inference neural network system for EEG and stabilometry signals classification

Abstract

The focus of this chapter is to study feature extraction and pattern classification methods from two medical areas, Stabilometry and Electroencephalography (EEG). Stabilometry is the branch of medicine responsible for examining balance in human beings. Balance and dizziness disorders are probably two of the most common illnesses that physicians have to deal with. In Stabilometry, the key nuggets of information in a time series signal are concentrated within definite time periods are known as events. In this chapter, two feature extraction schemes have been developed to identify and characterise the events in Stabilometry and EEG signals. Based on these extracted features, an Adaptive Fuzzy Inference Neural network has been applied for classification of Stabilometry and EEG signals. The model constructs its initial rules by a hybrid supervised/unsupervised clustering scheme while its final fuzzy rule base is optimised through competitive learning. A two-stage learning methodology is applied to this Neuro-Fuzzy structure, by incorporating gradient descent and recursive least squares estimations. The proposed modelling scheme is characterised by its high performance accuracy, high training speed and provides an efficient solution to the "curse of dimensionality" problem inherited in traditional neuro-fuzzy schemes. In order to classify Stabilometric time series, a set of balance-related features have been extracted according to the expert's criteria. The proposed Stabilometric medical diagnostic system is based on a method for generating reference models from a set of time series. The experimental results validated the proposed methodology. © 2011 Springer-Verlag Berlin Heidelberg.