Olfactory stimulation-based EEG acquisition and emotion recognition method and system

Abstract

The invention discloses an olfactory stimulation-based EEG acquisition and emotion recognition method and system, and the method comprises the steps: an experimental paradigm design module designs a novel paradigm so as to improve the emotion experience of a subject through adding olfactory stimulation while there is visual stimulation; a data acquisition module is used for selecting a proper testee to perform EEG signal acquisition and obtaining a preliminary emotion feedback label of the testee; a preprocessing module is used for preprocessing the collected EEG signals to obtain purer EEG signals; a feature extraction module is used for extracting four different emotional features of PSD, DE, DASM and RASM from the processed EEG signals; and a classification identification module dividesthe extracted features into a test set and a training set and puts the test set and the training set into a support vector machine SVM classifier for learning classification. The brain topographic map and the recognition rate under pure video stimulation and smell video mixed stimulation are compared, and therefore it is confirmed that smell stimulation can more intensively induce the emotion ofa subject.

Description

technical field [0001] The invention relates to the technical field of EEG signal processing, in particular to the fields of EEG signal acquisition under olfactory stimulation, machine learning, smell and vision, and multi-label classification, in particular to an olfactory stimulation-based EEG acquisition and emotion recognition method and its system. Background technique [0002] Emotion plays an important role in human-computer communication and social activities. Emotion recognition, as an important field of artificial intelligence application, has broad application prospects in psychotherapy and disease prevention, and the results of cognitive theory and psychological experiments It has been shown that brain activity is closely related to emotion, so emotion recognition based on EEG signals has aroused strong interest of researchers. [0003] Current traditional multimedia components stimulate two senses of people: (1) vision; (2) hearing. Stimulate the visual senses...

AI Technical Summary

Problems solved by technology

However, olfactory stimulation will be adaptable, and it will not last as long as visual stimulation, which will cause certain difficulties in data collection.

And there is no publicly available EEG database based on olfactory stimuli in the world, which severely limits the research on the emotional mechanism induced by olfactory stimuli

Images