Objective and Subjective Evaluation of Online Error Correction during P300-Based Spelling

Abstract

Error potentials (ErrP) are alterations of EEG traces following the subject’s perception of erroneous feedbacks. They provide a way to recognize misinterpreted commands in brain-computer interfaces (BCI). However, this has been evaluated online in only a couple of studies and mostly with very few subjects. In this study, we implemented a P300-based BCI, including not only online error detection but also, for the first time, automatic correction. We evaluated it in 16 healthy volunteers. Whenever an error was detected, a new decision was made based on the second best guess of a probabilistic classifier. At the group level, correction did neither improve nor deteriorate spelling accuracy. However, automatic correction yielded a higher bit rate than a respelling strategy. Furthermore, the fine examination of interindividual differences in the efficiency of error correction and spelling clearly distinguished between two groups who differed according to individual specificity in ErrP detection. The high specificity group had larger evoked responses and made fewer errors which were corrected more efficiently, yielding a 4% improvement in spelling accuracy and a higher bit rate. Altogether, our results suggest that the more the subject is engaged into the task, the more useful and well accepted the automatic error correction.