Application Design And Research Of Brain Computer Interface System Based On VEP

Brain-computer interface(BCI) is a new kind of system that allows people to communicate with outside world without peripheral nerves and muscle. With the use of engineering technologies, man's thinking can directly change to control command of external devices. Currently, visual evoked potential(VEP) based BCI systems have maintained significant advantages both in recognition speed and accuracy, with these advantages, a growing number of researchers were attracted into this field.In this paper, starting from the practical application of BCI system, a system was designed for helping people with severe motor disabilities read books. Based on steadystate visual evoked potential(SSVEP), the system used CPLD platform to design the visual stimuli module. On the Visual C++ platform, a real-time program designed with canonical correlation analysis(CCA) was applied to extract and analyze EEG. In the end, control signals generated by the real-time program were acquired to control mouse movement and book reader operations like page turning. The system was tested on eight subjects, and the result showed that the accuracy rate of sending control commands and information transfer rate(ITR) were 94% and 40.98 bit/min respectively. This system can effectively improve the living conditions of people with disabilities who cannot communicate with the outside world.A brain-computer interface(BCI) based on code modulated visual evoked potential(c-VEP) is among the fastest BCIs that have ever been reported, but it has not yet been given a thorough study. In a c-VEP BCI, a pseudorandom binary M sequence and its time lag sequences are utilized for modulation of different stimuli and template matching is adopted as the method for target recognition. In chapter five, five experiments were devised to investigate the effect of stimulus specificity on target recognition and made an effort to find the optimal stimulus parameters such as size, color and proximity of the stimuli, length of modulation sequence and its lag between two adjacent stimuli. By changing the values of these parameters and measuring classification accuracy of the c-VEP BCI, optimal combination of these parameters can be attained. Experimental results of seven subjects showed that when the length of modulation sequence and its lag between adjacent stimuli are 63 bits and 4 bits respectively, white stimuli with size of visual angle 3.8° and spatial proximity of 4.8° yielded superior performance. These findings provide a basis for determining stimulus presentation for building a high-performance c-VEP based BCI system.