Electroencephalogram identity recognition method and system based on graph neural network

Abstract

The invention discloses an electroencephalogram identity recognition method and system based on a graph neural network. The method comprises the steps that electroencephalogram signals generated when a user executes identity recognition operation are collected; extracting image feature data from the electroencephalogram signals; and inputting the graph feature data into a pre-trained graph neural network to obtain an identity recognition result. According to the electroencephalogram identity authentication method based on the graph neural network, time features and space features of electroencephalogram signals can be combined, abundant electroencephalogram data graph topological structure features are introduced while electroencephalogram single-channel features are reserved by constructing user graph data, electroencephalogram signals of different individuals can be better modeled, and the user experience is improved. The overfitting problem of traditional classification is reduced, the classification accuracy is improved, and better interpretability is achieved.

Description

technical field [0001] The invention relates to identification technology, in particular to a method and system for EEG identification based on a graph neural network. Background technique [0002] With the increasing demand for security, biometric-based authentication systems have attracted much attention. EEG signals have been widely studied by researchers due to their high reliability, secrecy and non-replicability. At present, many EEG-based identity authentication methods have been proposed. However, most of the classification methods used in these methods process EEG signals as a multi-channel time series, but do not take advantage of the natural spatial features and topological relationships between EEG signal channels, so it is easy to generate classifiers Fake features are learned resulting in overfitting problems. SUMMARY OF THE INVENTION [0003] The technical problem to be solved by the present invention: in view of the above-mentioned problems in the prior ...

AI Technical Summary

Problems solved by technology

However, most of the classification methods used in these methods process EEG signals as a multi-channel time series, but do not take advantage of the natural spatial features and topological relationships between EEG signal channels, so it is easy to generate classifiers. False features are learned to cause overfitting problems

Images