Abstract
Many recent studies have focused on improving the performance of event-related potential (ERP) based brain computer interfaces (BCIs). The use of a face pattern has been shown to obtain high classification accuracies and information transfer rates (ITRs) by evoking discriminative ERPs (N200 and N400) in addition to P300 potentials. Recently, it has been proved that the performance of traditional P300-based BCIs could be improved through a modification of the mismatch pattern. In this paper, a mismatch inverted face pattern (MIF-pattern) was presented to improve the performance of the inverted face pattern (IF-pattern), one of the state of the art patterns used in visual-based BCI systems. Ten subjects attended in this experiment. The result showed that the mismatch inverted face pattern could evoke significantly larger vertex positive potentials (p < 0.05) and N400s (p < 0.05) compared to the inverted face pattern. The classification accuracy (mean accuracy is 99.58%) and ITRs (mean bit rate is 27.88 bit/min) of the mismatch inverted face pattern was significantly higher than that of the inverted face pattern (p < 0.05).
Highlights
Brain-computer interfaces (BCIs) are intended to help patients to communicate with other people or control external devices through their brain activity (Wolpaw et al, 2000b; He et al, 2013)
Since the classification accuracy was not normally distributed, a nonparametric Kendall test was used to test the differences in classification accuracies between the SF and mismatch inverted face (MIF) patterns
Paired samples t-tests were used to test the differences between the MIF- and inverted face (IF)-patterns in terms of bit rates
Summary
Brain-computer interfaces (BCIs) are intended to help patients to communicate with other people or control external devices through their brain activity (Wolpaw et al, 2000b; He et al, 2013). The study showed the potential value of ERP-based BCIs for designing speller systems. Optimized classifiers were presented to improve the classification accuracy when only a few trials were used for constructing the average ERP (Zhang Y. et al, 2013). Hong et al reported that motion onset potentials (the N200) evoked by moving targets could be used to improve the performance of ERP-based BCIs (Hong et al, 2009). Long et al designed a BCI system using P300 and motor imagery for multi-degree control of a wheelchair (Long et al, 2012) and Yin et al combined P300 and steady-state visually evoked potential (SSVEP) brain signals for a high-performance BCI-based speller system (Yin et al, 2013, 2014, 2015)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
