Objective. This work aims to present a deeper investigation of the classification performance achieved by a motor imagery (MI) EEG-based brain-computer interface (BCI) using functional connectivity (FC) measures as features. The analysis is performed for two different datasets and analytical setups, including an information-theoretic based FC estimator (correntropy). Approach. In the first setup, using data acquired by our group, correntropy was compared to Pearson and Spearman correlations for FC estimation followed by graph-based feature extraction and two different classification strategies -linear discriminant analysis (LDA) and extreme learning machines (ELMs) -coupled with a wrapper for feature selection in the mu (7-13 Hz) and beta (13-30 Hz) frequency bands. In the second setup, the BCI competition IV dataset 2a was considered for a broader comparison. Main results. For our own database the correntropy / degree centrality / ELM approach resulted in the most solid framework, with overall classification error as low as 5%. When using the BCI competition dataset, our best result provided a performance comparable to those of the top three competitors. Significance. Correntropy was shown to be the best FC estimator in all analyzed situations in the first experimental setup, capturing the signal temporal behavior and being less sensitive to outliers. The second experimental setup showed that the inclusion of different frequency bands can bring more information and improve the classification performance. Finally, our results pointed towards the importance of the joint use of different graph measures for the classification.
Objective. Adapted from the concept of channel capacity, the information transfer rate (ITR) has been widely used to evaluate the performance of a brain–computer interface (BCI). However, its traditional formula considers the model of a discrete memoryless channel in which the transition matrix presents very particular symmetries. As an alternative to compute the ITR, this work indicates a more general closed-form expression—also based on that channel model, but with less restrictive assumptions—and, with the aid of a selection heuristic based on a wrapper algorithm, extends such formula to detect classes that deteriorate the operation of a BCI system. Approach. The benchmark is a steady-state visually evoked potential (SSVEP)-based BCI dataset with 40 frequencies/classes, in which two scenarios are tested: (1) our proposed formula is used and the classes are gradually evaluated in the order of the class labels provided with the dataset; and (2) the same formula is used but with the classes evaluated progressively by a wrapper algorithm. In both scenarios, the canonical correlation analysis (CCA) is the tool to detect SSVEPs. Main results. Before and after class selection using this alternative ITR, the average capacity among all subjects goes from 3.71 1.68 to 4.79 0.70 bits per symbol, with p -value <0.01, and, for a supposedly BCI-illiterate subject, her/his capacity goes from 1.53 to 3.90 bits per symbol. Significance. Besides indicating a consistent formula to compute ITR, this work provides an efficient method to perform channel assessment in the context of a BCI experiment and argues that such method can be used to study BCI illiteracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.