چكيده به لاتين
Noninvasive brain-computer interfaces (BCIs) have been of huge interest because of their potential. A noninvasive recording procedure is safer and its recording device is less expensive than for invasive procedures. Further-more, it is relatively easy to apply and large human population tests are possible. Many interesting studies have examined the feasibility of noninvasive BCI for applications for either physically disabled or healthy people: reactive BCIs using P300 potential or steady state visually evoked potential(SSVEP), and active BCIs based on sensorimotor rhythm. Although noninvasive BCI techniques have been significantly improved, their practical real-world usage has yet to be realized. This is because current noninvasive BCIs are still of limited frequency range and are usually restricted to binary commands. In addition, the information transfer rate is low for communication.
To extend its applicability, even with the limitations, attention has been paid to hybrid BCI. The concept of hybrid BCI suggests using different brain signal protocols together or even combining non brain signals. In this way, more extended control capacity is realized. Among the various possible combinations of signals, integrating simple interfaces together, for which each requires relatively little training, can be thought to enhance the convenience with respect to practical interface, while increasing the number of commands. There are some implementations of hybrid BCIs which combine EEG-based protocol with other protocols: fusion of EEG and electromyographic (EMG) activities, fusion of joystick and BCI controls and so on.
Steady-State visual evoked potentials (SSVEP) is a resonance phenomenon arising mainly in the visual cortex when a person is focusing the visual attention on a light source flickering with a frequency above 4 Hz. The SSVEP response is most commonly investigated using electroencephalography (EEG), i.e., with electrodes placed on the surface of the scalp. It consists of a periodic component of the same frequency as the flickering light source, as well as of a number of harmonic frequencies. The strongest response is obtained for stimulation frequencies in the range 5–20 Hz. Since the SSVEP is an intrinsic neuronal response which is relatively independent of higher level cognitive processes, it has been extensively used for studying low-level processing in the brain and for making clinical assessments of
visual pathways.
Electrooculograms(EOG) are taken with bi-polar electrodes on the outside of each eye. Exact electrode placements vary, but the electrodes are generally placed on the temples or on the distal ends of the forehead. When there is eye movement, a differential potential results that is also related to the magnitude of rotation. The development of eye tracking based control interfaces has a long history and has made significant progress. Eye movement input requires no intensive training and it operates impressively fast. In addition, eye movement can naturally express the user's focus of attention. It also makes some tasks performable for the physically disabled as well as older people.
In this work we design a hybrid BCI consists of SSVEP and EOG, that improves the accuracy of stimulus detection with respect to SSVEP BCI. For 16 stimulus state our BCI accuracy is 30% better than SSVEP-Based BCI.
Keywords: BCI, EEG, Hybrid BCI, SSVEP, EOG
