EEG Signal Classification using an Association Rule-Based Classifier

In this paper, the Electroencephalogram (EEG) of twenty schizophrenic patients and twenty age-matched healthy subjects are analyzed for classification purposes. Several features including AR model coefficients, band power and fractal dimension are extracted from EEG signals. This paper proposes a new classification method based on association rule mining. The system we propose consists of a preprocessing phase, a phase for mining the resulted transactional database, and a final phase to improve the resulted association rules. In this case, Fuzzy Accuracy-based Classifier System (F-XCS) is used to improve the resulted fuzzy associative rules for discriminating between healthy and schizophrenic subjects. The experimental results show that the method performs well reaching over 80% in accuracy.