EEG intent decoding method based on non-negative cp decomposition model

Abstract

The present invention provides an EEG intent decoding method based on a non-negative CP decomposition model. The method extracts the time component features of the EEG of different subjects in the boundary avoidance task, optimizes the feature dimension by using 2-DPCA, and uses The support vector machine classifies the features, which can reflect the differences in the EEG of the subject in different states, and the accuracy of the EEG classification of a single subject is high; and this method uses the interaction between the various modes of the EEG, and uses the channel The components and frequency components obtain the time component characteristics of the EEG, and the characteristics of the obtained EEG time components are well separable. By optimizing its dimension, it can effectively detect the left and right hand movements in the boundary avoidance task. EEG intent to decode.

Description

technical field [0001] The invention relates to the fields of biological signal processing and pattern recognition, in particular to an EEG intention decoding method based on a non-negative CP decomposition model. Background technique [0002] Electroencephalogram is a graph obtained by amplifying the spontaneous biopotential of the brain from the scalp through sophisticated electronic instruments. It is the spontaneous and rhythmic electrical activity of brain cell groups recorded by electrodes. The evaluation of brain activity is of great significance, and it is an important clinical tool for studying the functional state of the brain, and for the diagnosis and detection of neurological diseases. In EEG research, a key step is to effectively extract and identify subject-specific characteristic parameters from EEG. [0003] In cognitive neurorehabilitation, "motor imagery" therapy is often used to improve the cognitive dysfunction of stroke patients. During the process of ...

AI Technical Summary

Problems solved by technology

The extraction of characteristic parameters of EEG signals is of great significance to the diagnosis of neurological diseases. In the application of the traditional tensor discriminant analysis algorithm in the field of brain-computer interface, it usually focuses on extracting the frequency component of a single motor imagery EEG, and constructs The three-order tensor EEG data of time and time patterns realizes the optimized projection of different dimensions of EEG data including three patterns of time, frequency and space, and improves the recognition effect of motor imagery intentions. However, this is essentially an EEG feature. enhancement, ignoring the interaction between EEG modes

Images