Method for detecting and judging electroencephalogram signal caused by love impulse

Abstract

The invention discloses a method for detecting and judging an electroencephalogram signal caused by love impulse. The method comprises the following steps of: establishing a portrait photo material library; collecting electroencephalogram signal data Va; preprocessing the electroencephalogram signal data Va; dividing the electroencephalogram signal sections into two groups; performing channel dimension reduction processing; finding an effective brain region capable of distinguishing two states of love impulse and no love impulse and a component characteristic Fij of the effective brain region;and judging whether the electroencephalogram signal is caused by love impulse or not when the testee is stimulated by adopting a self-defined core algorithm.

Description

technical field [0001] The invention relates to the technical field of EEG signal detection, in particular to a method for detecting and determining an EEG signal caused by a love impulse. Background technique [0002] Numerous studies have shown that emotional stimuli can usually induce specific ERP components, such as P300 and late positive potential LPC. The researchers suggest that the induction of these specific ERP components may be related to motivated attention. The so-called motivated attention means that emotional stimuli can usually cause a higher degree of attention than neutral stimuli. The strength of this level of attention is reflected at the central nervous level, which means that the activity of neurons in related brain regions is enhanced or weakened. [0003] However, whether a stimulus can be regarded as an emotional stimulus depends not only on the stimulus material itself, but also on the state of the subjects when they receive the stimulus. If face...

AI Technical Summary

Problems solved by technology

In the prior art, most of the EEG signals are basically processed, and then the emotional changes corresponding to the EEG signals are determined by means of feature extraction and classifier training; The statistical distinction of electrical signals requires a large amount of experimental data. If the experimental data is insufficient or deviated, it will lead to errors in judgment results, and it is not convenient for in-depth analysis and research of EEG features to distinguish emotions through training and classification.

Whether it is through training classifiers or through machine learning to determine the type of emotion, the requirements for hardware equipment are relatively high, which will undoubtedly increase the application cost and access threshold to a certain extent.

Images