Imagination action EEG identification method based on fusion feature

Abstract

The invention relates to the field of EEG identification, can realize identification by taking an EEG signal as biological feature in the mode of imagination action, and is high in accuracy and repaid. In order to achieve the aim, the invention adopts the technical scheme that an imagination action EEG identification method based on fusion feature comprises the steps of: in the process of imagination action executed by a subject, collecting the corresponding EEG signal; after the pretreatment such as removing noise and the like, respectively extracting the EEG characteristic of a single channel and the cross-channel EEG characteristic of the opposite sides of cerebral hemisphere, and fusing the characteristics; then, carrying out dimension reducing operation on the fuse characteristic for optimizing and reconstructing; and finally, sending into a sorter for classified studying and testing, and achieving the aim of identification. The invention is mainly applied to EEG identification.

Description

technical field [0001] The invention relates to the field of electroencephalographic identification, in particular to an imaginative action electroencephalographic identification method based on fusion features. Background technique [0002] Biometric identification is the identification of personal identity through various high-tech information detection methods and the use of the inherent physiological or behavioral characteristics of the human body. Biological characteristics mainly include physiological characteristics and behavioral characteristics: physiological characteristics refer to innate and congenital physical characteristics of the human body, such as fingerprints, irises, palm shapes, faces, etc.; behavioral characteristics refer to the actions performed by people. The features extracted from sports are mostly acquired, such as handwriting, keystrokes, gait, etc. In the MIT Technology Review magazine in 2001, biometric technology was listed as one of the 10 m...

AI Technical Summary

Problems solved by technology

In contrast, some traditional biometrics (such as fingerprints or voices) may lose their own identification functions due to accidental damage (such as skin burns on the hands or loss of voice)

[0010] (4) EEG exists and only exists in the living body, so it can only be used for in-body detection. Compared with external features such as fingerprints, it is more difficult to copy and forge

However, a big bottleneck faced by the brain-computer interface system is the individual variability of EEG, which will inevitably lead to an increase in the complexity of the system design.

Images