Motion Imagination Research Based On EEG Signal

With the rapid development of computer technology in recent years,artificial intelligence has become increasingly hot.More and more experts and scholars began to study the combination of EEG signals and computers.Brain-computer interface technology establishes a direct connection path between human brain or animal brain and external devices such as computers.BCI technology translated brain's thinking activities into instructions that the computer can execute.Then it realize the interaction and control of the brain and external smart devices.BCI technology passes neuromuscular system of patient's injury.EEG signals what contain physiological state and instructions will be reused.It allows the brain to interact with the outside world and brings new hope to patients.This research is valued and it has broad peospects for development.In this paper,the EEG of motor imagery is the research object.According to the event related desynchronization and event related synchronization phenomena,this paper use four feature extractions such as energy feature extraction,common spatial pattern,dual-tree complex wavelet and approximate entropy.For the classification of EEG signals,support vector machine is used.The research points mainly include the following aspects:(1)Design experiment and collect data.The data used in this paper were collected by the researchers.20 college students were invited to conduct the experiment and then researchers collect their data,which was used for subsequent research.(2)The feature extraction method of EEG signals was studied.This paper use four feature extractions such as energy feature extraction,common spatial pattern,dual-tree complex wavelet and approximate entropy.Compare the accuracy of the final classification of various methods to obtain a better feature extraction method.(3)The method of pattern classification of EEG signals was studied.The support vector machine(SVM)classification method is mainly used to study the problem of finding the optimal parameters by improving the traditional grid search method when the radial basis kernel function is selected.The simulation results show that the improved algorithm is obviously.Improve the efficiency of finding the optimal parameters.