Classifying Multivariate ElectrocorticographicSignal Patterns from different sessions

Abstract: In the field of Brain-Computer Interfaces (BCI) there is a problem called the inter-session problem, generally causing a decrease in classification performance between sessions. This study investigates the extent of this problem in Electrocorticographic (ECoG) data, and how it may be approached using classification and feature selection algorithms. The focus regarding classification is whether linear or nonlinear classification methods generalizes better, and the focus of feature selection is whether filter or wrapper methods improve generalization more. These questions are answered by empirical experiments on two sets of ECoG data collected over two different sessions. The inter-session problem in ECoG data proved to be of considerable size. Classification performance dropped from 78-91% on the training data set (using cross validation) to 70-80% on the tests. Better normalizations and scaling methods were deemed necessary to help reduce this drop. The results were inconclusive as to linear or nonlinear classifier generalization, since performance was nearly identical. Due to their simplicity, linear methods would be preferable in this case. As to feature selection, the risks of overfitting became apparent using Simulated Annealing (SA) wrapper methods. Simpler feature selection algorithms that were less prone to overfitting, both filter and wrapper methods, helped to improve generalization more.