Feature extraction method for motor imagery electroencephalography signals

Abstract

The invention discloses a feature extraction method for motor imagery electroencephalography signals. The method includes the steps that the optimal time period for feature extraction of motor imageryelectroencephalography signals is determined according to the average power spectrum, then, four-layer double-tree complex wavelet decomposition is performed on the motor imagery electroencephalography signals within the time period, signal reconstruction is performed with the complex wavelet coefficient of each sub-band, and the average energy feature of data in the optimal time period of the reconstructed signals is calculated to serve as the time-frequency feature of the motor imagery electroencephalography signals; an IL-MVU algorithm is proposed to perform dimensionality reduction on thedata in the optimal time period of the reconstructed electroencephalography signals, low-dimensional vectors obtained after dimensionality reduction are taken as nonlinear features of the motor imagery electroencephalography signals, and finally standardization and feature fusion are performed on the time-frequency feature and nonlinear features of the motor imagery electroencephalography signalsin the optimal time period to obtain feature vectors of the motor imagery electroencephalography signals. The method greatly reduces the time consumption of the algorithm and improves the classification accuracy of the MI-EEG signals.

Description

technical field [0001] The invention belongs to an EEG signal processing method, and is specifically applied to feature extraction of motor imagery EEG signals in a Brain-Computer Interface (Brain-Computer Interface, BCI) system, and Landmark Maximum Variance Unfolding (L-MVU) for landmark points. ) was improved, and an incremental maximum expansion method of landmark points (Incremental, L-MVU, IL-MVU) was proposed, which was combined with Dual Tree Complex Wavelet Transform (DTCWT) to realize motion imagination Feature extraction and fusion of EEG signals. Background technique [0002] Motor Imagery Electroencephalography (MI-EEG) contains a lot of physiological information and is closely related to the state of consciousness. Therefore, the recognition of MI-EEG becomes the key in the brain-computer interface system, and the quality of features obtained from motor imagery EEG signals will directly affect the recognition accuracy. [0003] Motor imagery EEG signal is a k...

AI Technical Summary

Problems solved by technology

First, L-MVU can only reduce the dimensionality of a given data set, and cannot process new data in real time, making L-MVU insufficient in generalization ability for out-of-sample data, which is not conducive to the online implementation of the BCI system; Second, the nonlinear features extracted by L-MVU cannot reflect the time-frequency characteristics of MI-EEG, and the lack of time-frequency feature extraction will have a certain impact on the final pattern classification

Images