Improving the Cross-Subject Performance of the ERP-Based Brain-Computer Interface Using Rapid Serial Visual Presentation and Correlation Analysis Rank.

Shuang Liu,Ludan Zhang,Minpeng Xu,Wei Wang,Yue Sheng,Dong Ming

doi:10.3389/fnhum.2020.00296

Shuang Liu, Ludan Zhang + Show 4 more

Open Access

https://doi.org/10.3389/fnhum.2020.00296

Copy DOI

Abstract

The brain–computer interface (BCI) is a system that is designed to provide communication channels to anyone through a computer. Initially, it was suggested to help the disabled, but actually had been proposed a wider range of applications. However, the cross-subject recognition in BCI systems is difficult to break apart from the individual specific characteristics, unsteady characteristics, and environmental specific characteristics, which also makes it difficult to develop highly reliable and highly stable BCI systems. Rapid serial visual presentation (RSVP) is one of the most recent spellers with a clean, unified background and a single stimulus, which may evoke event-related potential (ERP) patterns with less individual difference. In order to build a BCI system that allows new users to use it directly without calibration or with less calibration time, RSVP was employed as evoked paradigm, then correlation analysis rank (CAR) algorithm was proposed to improve the cross-individual classification and simultaneously use as less training data as possible. Fifty-eight subjects took part in the experiments. The flash stimulation time is 200 ms, and the off time is 100 ms. The P300 component was locked to the target representation by time. The results showed that RSVP could evoke more similar ERP patterns among subjects compared with matrix paradigm. Then, the included angle cosine was calculated and counted for averaged ERP waveform between each two subjects. The average matching number of all subjects was 6 for the matrix paradigm, while for the RSVP paradigm, the average matching number range was 20 when the threshold value was set to 0.5, more than three times as much larger, quantificationally indicating that ERP waveforms evoked by the RSVP paradigm produced smaller individual differences, and it is more favorable for cross-subject classification. Information transfer rates (ITR) were also calculated for RSVP and matrix paradigms, and the RSVP paradigm got the average ITR of 43.18 bits/min, which was 13% higher than the matrix paradigm. Then, the receiver operating characteristic (ROC) curve value was computed and compared using the proposed CAR algorithm and traditional random selection. The results showed that the proposed CAR got significantly better performance than the traditional random selection and got the best AUC value of 0.8, while the traditional random selection only achieved 0.65. These encouraging results suggest that with proper evoked paradigm and classification methods, it is feasible to get stable performance across subjects for ERP-based BCI. Thus, our findings provide a new approach to improve BCI performances.

Highlights

Brain–computer interfaces (BCIs) are communication systems that allow people to send information to a computer or commands to other electronic devices by only measuring brain activities, without requiring any peripheral activity (Wolpaw et al, 2002)
The large EEG differences between individuals make it more difficult to realize the high performance on cross-subject BCI system, and the similar BCI-specific characteristics between individuals make it possible to have a wide application in universal BCI
Compared with the matrix paradigm, it is proved that the P300 signal induced by the Rapid Serial Visual Presentation (RSVP) paradigm had smaller individual differences, and the AUC value, which represented the performance of the classifier, was used as the evaluation index to analyze the within and cross-subject BCI systems

Summary

Introduction

Brain–computer interfaces (BCIs) are communication systems that allow people to send information to a computer or commands to other electronic devices by only measuring brain activities, without requiring any peripheral (muscular) activity (Wolpaw et al, 2002). Compared with all kinds of BCIs, the event-related potential (ERP)-based BCI has made great progress and achieved exciting results. The process from laboratory to application has encountered bottlenecks, facing three cross-problems, which are cross-subject, cross-time, and cross-scene. The Rapid Serial Visual Presentation (RSVP) can extract stable BCI specific features and strive to achieve high reliability cross-subject BCI technology, which can be used to expand the BCI approach to enable high throughput target image recognition applications (Sajda et al, 2003; Gerson et al, 2006; Bigdely-Shamlo et al, 2008). A common way here is to use an EEG speller system, which is a typical BCI system, by performing a clever paradigm to induce specific ERP components (e.g., P300 component)

Methods

Results

Discussion

Conclusion