Study On The Application Of Real-time BCI Based On FPGA

Brain-computer interface (BCI) is a kind of communication system that does notdepend on the normal output channels of brain. With the direct channel between brainand computer, BCI system can directly convert the information from brain into thecommands controling some peripherals. Therefore, BCI provides a valuable creativecommunication alternative to mortal gestures or language, which helps incommunicating or controling. BCI has drawn more and more attention for voriouspotential applications including rehabilitation medicine, industry, military affairs, andetc. However, BCI technologies are still under development, and most of which are inlaboratory stage.Facing the opportunity and challenge of BCI technology, the research of theapplication on real-time BCI based on FPGA is carried out in this paper. Compared withsteady-state visual evoked potential (VEP), transient visual evoked potential is easy tobe detected, and doesn’t easily cause visual fatigue. So, transient visual evoked potentialis used in the BCI system. Compared with DSP and SCM, FPGA performs well incomputing speed and logic control. So, FPGA is used as the core processing platform.According to the requirements of BCI applications, the new visual stimulator isdesigned by FPGA. The flashing mode of each stimulus module is that the black andwhite grids flash alternately, and the difference is the mark information. When the BCIis used to control SMS sending, there are two stimulus interfaces. First, the testeechooses the receiver of SMS, and then chooses the content of SMS. Each option islabeled by Chinese word. When the BCI is used to control lamp and fan, the fourcorrespond to the off or on of the lamp and fan. Each option is labeled by figure.The most important study on BCI technology is to find the suitable algorithms toextract weak VEP from strong background noise, and recognize the VEP signal. Havingcampared wavelet decomposition, PCA, KNN and BP neuron network,5scale db5isselected to decompose the averaged signal. D5and D4are selected as the feature ofVEP. Then BP neuron network is selected to recognize VEP. At the same time,generation algorithm is used to optimize BP neuron network. For real-time BCI, thewavelet decomposition and BP neuron network were realized on Nios II system.In this paper, the BCI system is used to control SMS sending. FPGA converts therecognized result of the VEP to the command of sending SMS. With serial port, FPGA cansend AT commands to TC35module and get relative acknowledge messages from TC35. In this way, SMS is sent. The BCI system is also used to control lamp and fan. FPGA converts the recognizedresult to command, controls the state of lamp and fan by controlling the state of the delay.Experiments illustrates that the selected algorithms is excellent in recognition rate.Further more, it is feasible to use the FPGA-based real-time BCI to controlSMS-sending and states of the lamp and the fan.