Symbol transfer entropy and brain network feature calculation method based on time-frequency energy

Abstract

The invention discloses a symbol transfer entropy and brain network feature calculation method based on time-frequency energy, which comprises the following steps: firstly, preprocessing collected motor imagery electroencephalogram signals (MI-EEG) based on common average reference; then, continuous wavelet transform is carried out on each lead MI-EEG, a time-frequency-energy matrix of each lead MI-EEG is obtained, time-energy sequences corresponding to each frequency in a frequency band closely related to motor imagery are spliced in sequence, and a one-dimensional time-frequency energy sequence of the lead is obtained; further, symbol transfer entropy between any two lead time-frequency energy sequences is calculated, a brain connectivity matrix is constructed, and matrix elements are optimized by using a Pearson feature selection algorithm; and finally, calculating the degree and the middle centrality of the brain function network, and forming a feature vector for MI-EEG classification. The result shows that the frequency domain feature and the nonlinear feature of the MI-EEG can be effectively extracted, and compared with a traditional feature extraction method based on the brain function network, the method has obvious advantages.

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. Specifically involved: constructing a dynamic brain function network based on continuous wavelet transform and symbol transfer entropy, and combining Pearson feature selection algorithm to optimize network features for the identification of different motor imagery EEG signals. Background technique [0002] The human brain is a complex and dense network 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 properties and discover potential information transmission relationships between brain network nodes. M...

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