A rule based approach to classification of EEG datasets: A comparison between ANFIS and rough sets

This paper compares two different rule based classification methods in order to evaluate their relative efficiency with respect to classification accuracy and the caliber of the resulting rules. Specifically, the application of adaptive neuro-fuzzy inference system (ANFIS) and rough sets were deployed on a complete dataset consisting of electroencephalogram (EEG) data. The results indicate that both were able to classify this dataset accurately and the number of rules were similar in both cases, provided the dataset was pre-processed using PCA in the case of ANFIS.