The Research Implement Of The Wireless And Real-time Bci Based On TSVEP

Brain Computer Interface(BCI) is an EEG-based communication and control system between human and computer or other electric devices,which does not depend on the brain's normal output pathways(peripheral nerves and muscles).BCI is a new communication and control mode.One of important use is that BCI can provide a communication and control channel for those with severe movement disabilities to improve their quality of life.BCI research has drawn attention of scientists in the brain-science,calculator,engineering,biomedical engineering and human machine automatic control.However,BCI technology is still under development.Current BCI also has many problems,such as low communication speed,systems scattered and unstability.There is a long distance from practical Application.This paper presents a real-time and wireless Brain Computer Interface system based on wearable technique and wireless communication technique.Main research contents are as follows:1. Design EEG signal acquisition circuit for the brain accurate collection;2. Form a wearable wireless communication network based on wearable technique and wireless communication technique to achieve EEG data transmittion and receive;3. Achieve visual stimulation device software development by using Microsoft Visual Studio.NET 2003 in the Windows environment;4. Use the combination algorithms of cumulative average and wavelet analysis for fast extraction and recognition of visual evoked potential,and study how to achieve the rapid classification of visual evoked potential with SVM algorithms.One of the key problems needs to be solved is the synchronization between the EEG signal acquisition and visual stimulation device.After collecting EEG signals, the wearable headband transmits the EEG signals and stimulating synchronization beacon signals to a computer. According to synchronize beacon signal, the computer generates a stimulating pattern. Experiments show that the design of wireless brain-computer interface system can achieve EEG signals accurately collection,transmittion and receive as well as real-time visual evoked potential extraction and recognition. When the visual stimulation have four stimulus blocks, 10 subjects's results in the experimental show that the system reached 92% recognition accuracy as a whole, and the maximum communication speed can reach 30bits/min.