Brain-computer interface system with few channels and asynchronous control based on mi and ssvep dual paradigm

Abstract

The invention discloses a few-channel asynchronous control brain-computer interface system based on MI and SSVEP dual paradigms, and belongs to the technical field intersecting cognitive neuroscience, information processing, and automatic control. For the BCI system with few channels of EEG signals, the system adopts the motor imagery paradigm as the switch module of the BCI system, uses the steady-state visual evoked potential paradigm as the BCI multi-selection module, and connects the two modules in series to form an asynchronous control BCI system. The variable empirical mode decomposition algorithm decomposes the few-channel EEG signal into multiple intrinsic mode functions. Based on the spectrum distribution characteristics of MI, IMF is selected as the feature to realize MI classification, and an improved canonical correlation analysis method is proposed to calculate the relationship between IMF and each SSVEP frequency template. The typical correlation coefficient of SSVEP is optimized, and the optimal typical correlation coefficient is selected to realize the classification of SSVEP, which can improve the control effect and classification accuracy of the few-channel BCI system.

Description

technical field [0001] The invention discloses a brain-computer interface system with fewer channels and asynchronous control based on dual paradigms of MI and SSVEP, and in particular relates to an asynchronous control brain-computer interface system composed of two paradigms of serial motor imagery and steady-state visual evoked potential, belonging to cognitive neuroscience. A technical field where science, information processing, and automation control intersect. Background technique [0002] Brain-Computer Interface (BCI) is an information exchange and control channel established between the brain and the external environment. People can use this channel to control external devices through brain awareness. The key to the BCI system is to accurately classify the brain's control consciousness, so as to realize different control instructions. Effective feature extraction and classification of brain signals is a key technology related to the performance indicators of BCI ...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to address the shortcomings of the above-mentioned background technology, and provide a brain-computer interface system with few channels and asynchronous control based on MI and SSVEP dual paradigms, and realize the multi-selection function of the BCI system through MI paradigm BCI and SSVEP paradigm BCI connected in series. Asynchronous control, solves the technical problems that the classification options of the MI paradigm in the few-channel BCI system are few, the SSVEP paradigm cannot realize asynchronous control, the signal quality of the few-channel BCI is poor, and the classification accuracy rate needs to be improved

Images