A Multi-Class Tactile Brain–Computer Interface Based on Stimulus-Induced Oscillatory Dynamics

Abstract

Abstract-We proposed a multi-class tactile brain-computer interface that utilizes stimulus-induced oscillatory dynamics. It was hypothesized that somatosensory attention can modulate tactile induced oscillation changes, which can decode different sensation attention tasks. Subjects performed four tactile attention tasks, prompted by cues presented in random order and while both wrists were simultaneously stimulated: 1) selective sensation on left hand (SS-L), 2) selective sensation on right hand (SS-R), 3) bilateral selective sensation (SS-B), and 4) selective sensation suppressed or idle state (SS-S). The classification accuracy between SS-L and SS-R (79.9±8.7%) was comparable with that of a previous tactile BCI system based on selective sensation. Moreover, the accuracy could be improved to an average of 90.3±4.9% by optimal class-pair and frequency-band selection. Three-class discrimination had accuracy of 75.2±8.3%, with the best discrimination reached for the classes SS-L, SS-R and SS-S. Finally, four classes were classified with accuracy of 59.4±7.3%. These results show that the proposed system is a promising new paradigm for multi-class BCI.

Performance of Brain–Computer Interfacing Based on Tactile Selective Sensation and Motor Imagery

“…In six out of seven experimental sets [18], [19], [23], [41], [53]- [55] (as seen in table 1), EEG signals were recorded using a SynAmps2 system (Neuroscan, U.S.A.). A 64-channel quick-cap was used to collect 62-channel EEG signals, and the electrodes were placed according to the extended 10/20 system.…”

“…Twenty subjects participated in the second SS protocol [41], with the g.Tec system. During the SS task period, sustained vibrotactile stimuli were simultaneously applied to both wrists.…”

“…Recently, in a series of studies, we proposed a tactile BCI based on oscillatory dynamics from the somatosensory area of the cortex, which we termed selective sensation (SS) tactile BCI [18], [19], [40], [41]. This approach is based on the observation that mental processing of afferent inflow in the human somatosensory system also induces ERD/ERS [42], [43] [44].…”

Decoding Covert Somatosensory Attention by a BCI System Calibrated With Tactile Sensation

“…This system achieved a mean accuracy of 72% in 11 subjects, when selecting between two targets. By comparison, we have shown that BCI based on tactile selective sensation has largely increased tactile BCI performance by approximately 10%, and this tactile BCI modality based on SS substantially outperformed previous tactile BCI systems, making it potentially applicable to a larger number of users [36], [37]. The ERD/ERS oscillatory response and SSSEP response provide complementary information of the somatosensory input processing.…”

“…Brain oscillatory dynamics, as quantified by event related desynchronization/synchronization (ERD/ERS) [31], [32], are not only correlated with real or imagined movement, but also with external sensory stimulation processing [33], [34]. We have previously shown that tactile-induced oscillatory dynamics provide a reliable brain signal modality for a tactile BCI [35]- [37]. Furthermore, this oscillatory activity is not only correlated with real tactile sensation, but also with imagined sensation [15].…”