P300-SSVEP-based brain-computer interface method of large instruction set

Abstract

The invention relates to a brain-computer interface (BCI), aims to provide a new hybrid brain-computer interface (HBCI) paradigm which is capable of simultaneously evoking an SSVEP (Steady-State Visual Evoked Potential) signal and a P300 signal, and firstly provides an evoking strategy of a 108-instruction set which achieves purposes of increasing of the instruction set and a high information transfer rate (ITR). A brain-computer interface system of the large instruction set and the high information transfer rate is expected to obtain considerable social and economic benefits. Therefore, a P300-SSVEP-based brain-computer interface method of the large instruction set of the invention comprises the steps of: building an experiment platform, wherein the platform specifically comprises an electroencephalography (EEG) electrode, an electroencephalography amplifier and computers, designing the new paradigm for stimulation, collecting P300 and SSVEP data, carrying out data processing in the computer, outputting classification accuracy (CA), and finally calculating the information transfer rate, wherein the data processing stage is to carry out identification classification through step-wise linear discriminant analysis (SWLDA) and a canonical correlation analysis method. The method is mainly applied to brain-computer interface occasions.

Description

technical field [0001] The present invention relates to a brain-computer interface, in particular, relates to a large instruction set brain-computer interface method based on P300-SSVEP. Background technique [0002] Brain-Computer Interface (BCI) is a communication system that does not rely on the normal output pathways composed of peripheral nerves and muscles. It recognizes specific brain signal patterns, which consist of five consecutive stages: signal acquisition, preprocessing (or signal enhancement), feature extraction, classification interface control. [0003] The signal acquisition stage captures the brain signal and performs signal noise reduction and hardware processing. The preprocessing stage prepares the signal in an appropriate form for subsequent processing. The feature extraction stage is to identify the information in the extracted brain signal and map it to a feature vector containing an effective discriminant function. This is a very challenging task. ...

AI Technical Summary

Problems solved by technology

[0005] In recent years, the brain-computer interface has achieved rapid development in terms of improving feature recognition algorithms and achieving high information transmission rates, but there are still some limitations. For example, the expansion of the instruction set leads to a decrease in the information transmission rate. The existence of the relationship greatly limits the development pace of the brain-computer interface, so the research on the brain-computer interface system with a large instruction set and high information transmission rate urgently needs to break through the bottleneck and further explore

Images