Classification of Imagined Beats for use in a Brain Computer Interface

Abstract

The power spectrum of an EEG signal shows differences with respect to its baseline the moment a subject is hearing, or expecting, a tone. As this difference also occurs when one is not actually hearing it, a Brain Computer Interface can be developed in which imagined rhythms are used to transfer information. Four healthy subjects participated in this study in which they had to imagine a simple rhythm. A metronome was kept ticking so that the subjects would not drift in their tempo. Solely based on the EEG signals, the classifier had to distinguish between imagined accented and non-accented tones. The features for the classification were automatically selected out of a set of possible features that focussed on phase and power differences of independent components. The classification rate found is about 0.6 for two of the four subjects, and several classifications can be combined to increase this classification rate to values larger than 0.7 with 2 s worth of data for the best performing subject. Chance level for our classification task is 0.5.

The effect of distinct mental strategies on classification performance for brain–computer interfaces

“…In our ease-scale, NAV and AUD were as well rated descriptively least demanding, but the MOTOR task was not rated more difficult than non-motor tasks in general. In the study of De Kruif et al (2007), 2 of 4 participants gained control, and the best accuracy was 73% in one session. They used different accented tones in auditory imagery, while we used tasks from very different domains (e.g.…”

“…Cabrera and Dremstrup (2008) implemented a BCI with an auditory imagery and a spatial navigation imagery task and confirmed these findings. De Kruif et al (2007) designed a BCI which was completely controlled by auditory imagination: The classification discriminated between accented versus non accented tones within an imagined rhythm. Dyson et al (2010) examined relevant electrode positions for various mental tasks.…”

Design requirements and potential target users for brain-computer interfaces – recommendations from rehabilitation professionals

“…BCI paradigms should use more intuitive strategies. This could mean, for example, that BCIs based on mental imagery of movement, [48] musical rhythms [49,50] or calculation [51] are, even if feasible, not usable strategies for target users.…”

The brain–computer interface cycle

“…Among imagery tasks, motor imagery is currently the most popular [13]. Other imagery tasks include visual imagery [19], mental navigation [20] and music imagery [20][21][22][23]. Higher level cognitive tasks such as word association and mental arithmetic are often used in cross-modal BCIs, where the classes to be distinguished do not all fall within the same modality [19,24].…”