Method for detecting P300 electroencephalogram based on convolutional neural network

Abstract

The invention discloses a method for detecting a P300 electroencephalogram based on a convolutional neural network, which is used for a brain-computer interface classification algorithm and is capable of effectively solving a small sample problem in the conventional classification algorithm while improving the classification accuracy. Through using a thought of an image recognition field for reference, the method fully utilizes thoughts of a local receptive field and weight sharing of the convolutional neural network to take a typical P300 electroencephalogram acquisition sample as an analogy of a feature image, the sample characteristics are extracted through a continuous convolution process, and through carrying out feature mapping on a down sampling process, feature extraction and feature mapping are continuously performed, so that the sample characteristics are more simplified, meanwhile, through applying the local receptive field and weight sharing, network weighting parameters and computation complexity are greatly reduced to facilitate popularization of the algorithm. The experimental result shows that through the method adopted in the invention, the classification accuracy is effectively improved, the system stability is increased, and the method has better application prospect.

Description

technical field [0001] The present invention relates to a signal detection technology, in particular to a P300 EEG signal detection method based on a convolutional neural network. Background technique [0002] With the continuous development of artificial intelligence technology, research based on human vital signs has attracted more and more attention, among which the research on eyes, face and EEG is the most concentrated. Brain-computer interface technology, as a research hotspot in recent years, has made great progress, especially in the medical field, and intelligent wheelchairs based on EEG signals have brought good news to patients with impaired physical functions. For example, the patent application document of “A Novel Intelligent Wheelchair System Based on Motor Imagery EEG Control” (201010249134.9) of Beijing Normal University proposes a motor imagery-based wheelchair control method, which obtains EEG signals through the motor imagery paradigm, Obtain the control...

AI Technical Summary

Problems solved by technology

However, the traditional classification method also has many shortcomings: it is easy to produce small sample problems, the demand for training samples is too large, the system is not stable enough, etc.

[0006] 1 The brain-computer interface based on motor imagery or SSVEP has poor stability, and the accuracy of signal detection is low, generally below 80%;

[0007] 2 The traditional classification method based on P300 EEG signals takes a long time to train and requires a large number of training samples;

[0008] 3 The traditional classification method based on P300 EEG signals has a small sample problem, and the accuracy rate drops sharply when the sample size is smaller than the sample dimension;

[0009] 4 The traditional classification method based on P300 signal can get better classification accuracy when there are enough samples, but the accuracy is not good when there are fewer samples;

Images