Feature recognition system and method for electroencephalogram signals

Abstract

Provided are a feature recognition system and method for electroencephalogram signals. The method comprises the following steps: utilizing four conduction electrodes of a temporal area above ears to collect original brain electrical signals in different emotion states of different people and forming a sample set; obtaining electroencephalogram feature data from the sample set by pre-processing and extracting features; carry out smoothing operation on electroencephalogram feature data to obtain a training sample used for training a support vector machine so that an emotion recognition classifier is obtained. The feature recognition system and method for electroencephalogram signals have the following beneficial effects: under the premise that acquisition cost and complexity of electroencephalogram are greatly reduced, the feature recognition system and method can maintain higher emotion recognition accuracy and provide useful reference on emotion recognition by wearable equipment.

Description

technical field [0001] The present invention relates to a technology in the field of EEG signal detection, in particular to an EEG signal feature recognition system and method based on four conductive electrodes above the ear. Background technique [0002] Emotions can reflect a person's cognition and attitude, can affect people's psychology and behavior, and are an important part of people's daily life. With the rapid development of human-computer interaction applications, people hope to have more humanized computers to assist people in completing work tasks, which requires computers to have certain emotion recognition capabilities. In the process of human-computer interaction, if the computer can quickly and accurately identify the emotional state of the person, it can adjust its work content and methods according to the emotional state of the person, improve the experience of human-computer interaction, and make the process of human-computer interaction more efficient. F...

AI Technical Summary

Problems solved by technology

Although this method can collect relatively stable EEG signals, its disadvantage is that the subject needs to apply conductive paste for each collection. The workload of this process is huge, and the preparation process is also very cumbersome. Prolonged exposure can cause discomfort

In addition, the EEG signals in all electrodes may have redundant information that has nothing to do with emotions. If all of them are used, it will not only increase the complexity of the algorithm, but also interfere with emotion recognition and reduce the accuracy of emotion recognition.

Images