Lead selection method for emotional electroencephalogram based on independent component analysis

Abstract

The invention discloses a lead selection method for emotional electroencephalogram based on independent component analysis. A multi-lead emotional electroencephalogram is utilized for conducting filtering processing, ICA analysis is conducted on data after filtering, spatial filter sets corresponding to different emotional task backgrounds are constructed, and linear projection is conducted; spatial feature parameters of a full-lead emotional signal are acquired, and then the lead selection method is utilized for selecting the optimum lead set of a subject. According to the method, higher recognition accuracy rate is acquired, it is achieved that different subjects can automatically select emotion-related independent components, and compared with a mode of extracting the independent component of a full-passage, the independent component of the optimum lead position not only can reduce the time complexity of an algorithm but also can accurately describe the real conditions of an emotion-related independent source and effectively inhibit the components which are not related with emotional signals and the interference caused by external noises.

Description

technical field [0001] The invention relates to the technical field of brain-computer interface, in particular to a lead selection method of emotional EEG signals based on independent component analysis. Background technique [0002] The emotional pattern triggered by a person when performing a specific activity can reveal his emotional behavior state to a large extent, such as: positive, neutral, negative, etc., and this emotional pattern can be obtained by tracking the changes in scalp EEG , so the design and implementation of emotion recognition algorithms based on EEG signals has become a new research hotspot. EEG emotion recognition refers to the use of EEG signals as the observed object, through its analysis and identification, to obtain information such as the emotional type of the observed object. In the process of emotion recognition, the analysis of emotion EEG signal is the most critical step, for this reason, researchers have done a lot of research. Among them,...

AI Technical Summary

Problems solved by technology

Among them, Soleymani proposed to use the original EEG signal in theta (4Hz<f<8Hz), slow alpha (8Hz<f<10Hz), alpha (8Hz<f<12Hz), beta (12Hz<f<30Hz) and gamma (30Hz< f) The power spectrum on the 5 frequency bands and the asymmetry features of the left and right brain power spectrum on the 4 frequency bands except slowsalpha have achieved some success in emotion recognition, but this kind of method mainly focuses on the frequency of the emotional signal Domain analysis, the analysis process only considers the frequency domain information of the signal, it is difficult to guarantee the recognition accuracy of emotional signals

[0003] At this stage, the research on emotion recognition based on independent component analysis to extract the full-lead independent components of emotional EEG signals has been realized, but the algorithm complexity of emotion recognition based on multi-lead EEG signals is too high, and some studies have found that some lead Linked EEG signals are poorly correlated with emotional processes

Sander et al. proposed that the power spectral density on different frequency bands is more correlated with Fp1, T7, CP1, Oz, Fp2, F8, FC6, FC2, Cz, C4, T8, CP6, CP2, and PO4. Chatchinarat et al. found that the frontal cortex and The leads of the parietal lobe are more important in the process of emotion recognition, however, these studies ignore the variability between subjects and are based on manual selection of multiple leads

Images