A method for calculating symbol transfer entropy and brain network characteristics based on time-frequency energy

Abstract

The invention discloses a method for calculating symbol transfer entropy and brain network characteristics based on time-frequency energy. First, the collected motor imagery EEG signals (MI-EEG) are preprocessed based on a common average reference; MI-EEG performs continuous wavelet transform to obtain its time-frequency-energy matrix, and splices the time-energy sequences corresponding to each frequency in the frequency band closely related to motor imagery in turn to obtain the one-dimensional time-frequency energy of the lead sequence; then, calculate the sign transfer entropy between any two lead time-frequency energy sequences, construct a brain connectivity matrix, and use the Pearson feature selection algorithm to optimize the matrix elements; finally, calculate the degree and betweenness centrality of the brain functional network , constituting the feature vector for MI‑EEG classification. The results show that the present invention can effectively extract the frequency domain features and nonlinear features of MI-EEG, and has obvious advantages compared with the traditional feature extraction method based on brain function network.

Description

technical field [0001] The invention belongs to the field of EEG signal processing, and relates to a time-frequency energy-based symbol transfer entropy and brain network feature calculation method, which is applied to feature extraction of motor imagery EEG signals (MI-EEG) in a brain-computer interface system. It specifically involves: constructing a dynamic brain function network based on continuous wavelet transform and symbol transfer entropy, and optimizing the network features with the Pearson feature selection algorithm for the identification of different motor imagery EEG signals. Background technique [0002] The human brain is a complex and dense network consisting of billions of interconnected neurons. In recent years, complex network analysis methods based on graph theory have been applied in neuroscience. The basic principles of complex networks can be used to analyze brain attributes and discover potential information transfer relationships between brain netwo...

AI Technical Summary

Problems solved by technology

However, the traditional transfer entropy requires a large amount of data to estimate the probability distribution function, which is slow in calculation speed and susceptible to noise, which limits its application in the modeling of actual brain functional networks.

In addition, the existing technology directly constructs the brain function network by calculating the connectivity between the original EEG signals, which is difficult to obtain the frequency domain features of the EEG signal, making the final classification accuracy based on the brain function network feature extraction method generally low

Images