Identification method of multiple-motion imaging EEG signals

Abstract

The invention relates to an identification method of multiple-motion imaging EEG signals. The method comprises the steps of inputting a one-directional characteristic vector which is obtained throughpreprocessing and extraction fusion on a multiple-motion imaging EEG signal into a multi-core learning support vector machine, realizing identification according to an output classification result, wherein preprocessing comprises eliminating noise and ocular artifact, and extraction fusion comprises extracting a time frequency characteristic and a spatial domain characteristic by means of discretewavelet transform and one-to-many common space mode, and connecting the characteristics of the domains in an end-to-end manner for forming the one-dimensional characteristic vector; and obtaining parameters required for identifying the to-be-identified multiple-motion imaging EEG signal through an immune genetic algorithm. The identification method according to the invention effectively overcomesdefects of insufficient information description in a traditional single-domain characteristic extracting algorithm and relatively low identification rate of a single-core classifier. Through using multiple core corresponding fusion characteristics for corresponding with the characteristics of different domains, better robustness and relatively high identification rate of the identifier are realized.

Description

technical field [0001] The invention relates to the field of electroencephalogram signal identification, in particular to a method for identifying multi-type motor imagery electroencephalogram signals. Background technique [0002] With the development of computer technology and brain science, people began to try to build a communication pathway between the brain and the outside world. This pathway does not rely on the participation of peripheral nerves and muscle tissue, and can interpret brain signals into corresponding commands to achieve communication with the outside world. Communication and control, this pathway is named Brain Computer Interface (Brain Computer Interface, BCI). The application of BCI, a communication channel between human and the outside world, has also attracted people's attention in rehabilitation engineering and intelligent auxiliary robots. However, the brain-computer interface is a multidisciplinary technology, and the EEG signal is nonlinear and ...

AI Technical Summary

Problems solved by technology

The invention effectively overcomes the shortcomings of insufficient information description of traditional single-domain feature extraction algorithms and the low recognition rate of single-core classifiers, and provides a new idea for multi-type motor imagery EEG signal recognition

Images