Abstract

In the recognition of emotions based on EEG signals, the feature extraction used is as important as classifier for the results of classification. The better the feature extraction is used, the better the results of the classification. In the other hand, there is no definitive approach for feature extraction in emotion recognition based on EEG signal. In this paper, we use nine types of time frequency domains as features, Principal Component Analysis (PCA) as dimension reduction method and Back-propagation Neural Network as classifiers. This method is implemented using a database that can be accessed by the public. The results of the experiment show that time frequency domain feature extraction and back propagation can achieve 63.75 % recognition rate.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call