Electroencephalogram signal emotion recognition method and system fusing multiple features

Abstract

The invention discloses an electroencephalogram signal emotion recognition method and system fusing multiple features, and relates to the technical field of electroencephalogram signal emotion recognition, and the method mainly comprises the steps: obtaining emotion-induced original electroencephalogram signal data, and preprocessing the emotion-induced original electroencephalogram signal data; carrying out nonlinear feature and brain cognitive feature extraction on the preprocessed electroencephalogram signal data; fusing the nonlinear features and the brain cognitive features of the preprocessed electroencephalogram signal data by adopting a canonical correlation analysis algorithm to obtain fused electroencephalogram feature signals; and performing emotion recognition on the fused electroencephalogram characteristic signals by adopting a compressed sensing algorithm. The most complete characteristic parameters with the most discriminating capability can be constructed, the emotionrecognition effect of the electroencephalogram signals is improved, and meanwhile the defects that a traditional recognition model is high in training complexity and poor in anti-noise performance areovercome.

Description

technical field [0001] The invention relates to the technical field of EEG signal emotion recognition, in particular to an EEG signal emotion recognition method and system that integrates multiple features. Background technique [0002] EEG signal is a signal with many applications and relatively mature technology development. EEG signal contains rich emotional information, and as a kind of physiological signal, it is not affected by human subjective will and is more authentic. features. [0003] At present, the development of nonlinear dynamics has gradually matured, and the view of the brain as a nonlinear dynamic system has also been recognized by more and more researchers. As a typical non-stationary signal, EEG signals have nonlinear characteristics. The nonlinear characteristics of EEG signals are studied, and the feasibility of using nonlinear characteristics for EEG emotion recognition is proved. Morteza et al. determined the time window based on the signal complex...

AI Technical Summary

Problems solved by technology

[0007] In summary, in EEG signal emotion recognition, there are defects such as single recognition feature and incomplete information contained in the feature, and there are also problems such as high training complexity of traditional recognition model and poor anti-noise performance.

Images