No abstract

No abstract

P300 spellers are among the most popular brain-computer interface paradigms, and they are used for many clinical applications. However, building the classifier for identifying event-related potential (ERP) responses, i.e., calibrating the P300 speller, is still a time-consuming and user-dependent problem. This paper proposes a novel method to reduce calibration times significantly. In the proposed method, a small number of ERP epochs from the current user were used to build a reference epoch. Based on this reference, the Riemannian distance measurement was used to select similar ERP samples from an existing data pool, which contained other-subject ERP responses. Linear discriminant analysis (LDA), support vector machine, and stepwise LDA were trained as ERP classifiers on the selected database and then were used to identify the user-attended character. With only 12 s of EEG data to calibrate, an average character recognition accuracy for 55 subjects of up to 87.82% was obtained. The LDA that built on other-subject samples that were selected by Riemannian distance outperformed the other classifiers. Compared with other state-of-the-art studies, this method significantly reduces P300 speller calibration times, while maintaining the character recognition accuracy.

Brain-computer interfaces (BCIs), independent of the brain's normal output pathways, are attracting an increasing amount of attention as devices that extract neural information. As a typical type of BCI system, the steady-state visual evoked potential (SSVEP)-based BCIs possess a high signal-to-noise ratio and information transfer rate. However, the current high speed SSVEP-BCIs were implemented with subjects concentrating on stimuli, and intentionally avoided additional tasks as distractors. This paper aimed to investigate how a distracting simultaneous task, a verbal n-back task with different mental workload, would affect the performance of SSVEP-BCI. The results from fifteen subjects revealed that the recognition accuracy of SSVEP-BCI was significantly impaired by the distracting task, especially under a high mental workload. The average classification accuracy across all subjects dropped by 8.67% at most from 1- to 4-back, and there was a significant negative correlation (maximum r = −0.48, p < 0.001) between accuracy and subjective mental workload evaluation of the distracting task. This study suggests a potential hindrance for the SSVEP-BCI daily use, and then improvements should be investigated in the future studies.

No abstract