Towards a Cure for BCI Illiteracy

Abstract

Brain–Computer Interfaces (BCIs) allow a user to control a computer application by brain activity as acquired, e.g., by EEG. One of the biggest challenges in BCI research is to understand and solve the problem of “BCI Illiteracy”, which is that BCI control does not work for a non-negligible portion of users (estimated 15 to 30%). Here, we investigate the illiteracy problem in BCI systems which are based on the modulation of sensorimotor rhythms. In this paper, a sophisticated adaptation scheme is presented which guides the user from an initial subject-independent classifier that operates on simple features to a subject-optimized state-of-the-art classifier within one session while the user interacts the whole time with the same feedback application. While initial runs use supervised adaptation methods for robust co-adaptive learning of user and machine, final runs use unsupervised adaptation and therefore provide an unbiased measure of BCI performance. Using this approach, which does not involve any offline calibration measurement, good performance was obtained by good BCI participants (also one novice) after 3–6 min of adaptation. More importantly, the use of machine learning techniques allowed users who were unable to achieve successful feedback before to gain significant control over the BCI system. In particular, one participant had no peak of the sensory motor idle rhythm in the beginning of the experiment, but could develop such peak during the course of the session (and use voluntary modulation of its amplitude to control the feedback application).

The effect of multimodal and enriched feedback on SMR-BCI performance

“…In each group were also end-users who did not achieve any significant cursor control. This phenomenon is known as BCI illiteracy Kübler and Müller, 2007;Vidaurre and Blankertz, 2010), and it seems to be present in 10-30% of potential BCI end-users Guger et al, 2003). Approaches to alleviate this phenomenon have been explored, such as improved signal processing .…”

Using a motor imagery questionnaire to estimate the performance of a Brain–Computer Interface based on object oriented motor imagery

“…Swapping the 'optimal' features of the classifiers based on SI and GOI caused a significant decrease in classification accuracy. The effect of changes in the MI paradigm on classification accuracy was previously noticed in studies where off-line chosen features were used for on-line BCI with feedback [Vidaurre et al 2010] or when simple on-line feedback was replaced with a Virtual Reality environment [Pfurtscheller at al.2006b, Leeb et al 2007]. …”

Improving Physiological Signal Classification Using Logarithmic Quantization and a Progressive Calibration Technique

“…If the score on this additional testing procedure is below 75%, a commonly used threshold for BCI literacy (Vidaurre and Blankertz, 2010), the user will be prompted to record sixty seconds of the next candidate mental gesture (e.g. sport).…”

“…We calibrate 86.6% of users to a threshold of BCI literacy (75% accuracy) (Vidaurre and Blankertz, 2010) with under five minutes of training data, and 100% of users within half an hour. This paper is organized as follows.…”