EEG (electroencephalogram)-based emotion recognition method and system

Abstract

The invention discloses an EEG (electroencephalogram)-based emotion recognition method, which comprises the following steps of: inputting original data, and selecting a proper and public electroencephalogram data set with recognizable emotion tags; data preprocessing, wherein the collected EEG signals are preprocessed to obtain proper electroencephalogram signals; feature analysis: carrying out time domain and frequency domain feature analysis on the preprocessed EEG signal; feature processing: extracting six different emotion features from the analyzed EEG signals; and classification and identification: classifying the extracted features into a test set and a training set, and putting the test set and the training set into a support vector machine (SVM) classifier and a KNN classifier for learning and classification. The invention further discloses an emotion recognition system based on the EEG electroencephalogram signals. According to the method, electroencephalogram signals and recognition rates under different classifiers are compared, the recognition condition can be visually reflected, and meanwhile new electroencephalogram signal features are recognized based on a trained model.

Description

technical field [0001] The invention relates to the technical field of EEG signal processing, in particular to feature extraction and machine learning of EEG signals under video stimulation, and in particular to an emotion recognition method and system based on EEG signals. Background technique [0002] Emotion is a complex physiological and physical change process under external conditions, and it is a physiological and psychological state that integrates feelings, behaviors, and thoughts. Emotional intelligence refers to people's ability to recognize, understand, and apply emotions to guide behavior. Among the two mainstream signal research methods for emotion recognition at present, the speech and facial expression recognition based on biological emotional behavior can also provide research on emotion recognition, but because it can be controlled by artificial camouflage, it is difficult to ensure that signals reflecting real emotions can be obtained. , so that the true ...

AI Technical Summary

Problems solved by technology

Although the proposed methods of various research reports differ in the type of features extracted from EEG and the classifiers used, it is difficult to compare the reported results due to the use of different data sets.

Images