A single p300 detection method based on matrix gray modeling

Abstract

The present invention proposes a single P300 detection method based on matrix gray modeling, which belongs to the field of cognitive neuroscience and relates to a feature extraction and identification detection method of event-related potential P300, specifically a method based on gray theory A single-shot P300 detection method for matrix gray modeling. The method includes: 1. Preprocessing the original collected EEG signals; 2. Lead combination selection, according to the training set data target stimulation and non-target stimulation waveform diagrams, select the 4 leads with the most obvious waveform differences in the parieto-occipital region. 3. Carry out segmented matrix gray modeling on the data of 4 leads, and extract the model parameters as feature vectors; 4. Use the method of Fisher ratio value to select the optimal feature, and at the same time reduce the eigenvector The purpose of the dimension; 5. Use the support vector machine classifier to classify the feature vectors to realize the detection and recognition of a single P300. The experimental data test shows that the algorithm can improve the detection and recognition rate of a single detection of P300, and the correct recognition rate can be further improved when there are few superpositions.

Description

technical field [0001] The invention belongs to the field of cognitive neuroscience, and relates to a feature extraction and recognition detection method of event-related potential P300, in particular to a single P300 detection method based on matrix gray modeling in gray theory. Background technique [0002] P300 (also known as P3b) is an endogenous component that can reflect the advanced cognitive processing process. It is the largest late positive wave recorded in the scalp with a latency of about 300ms when the subject recognizes the "target stimulus". Evoked by visual, auditory and somatosensory stimuli. [0003] P300 potential is widely used in the research of brain-computer interface system (Brain Computer Interface, BCI) and psychological lie detection. The traditional P300 identification method adopts the time-domain coherent averaging method, and the background random noise can be effectively reduced by superimposing and averaging. This method can identify P300 v...

AI Technical Summary

Problems solved by technology

[0008] In order to solve the defects of low accuracy and low practicability of the single P300 extraction method in the prior art, the present invention provides a P300 feature extraction method based on matrix gray modeling, which constructs the P300 signal through matrix gray modeling Model, the model parameters are used as features, so that the effect of P300 classification and recognition is better improved, and the detection and recognition rate of P300 signal is improved while reducing the number of stimulation repetitions

Images