Classification of electroencephalography signals using three-dimensions convolution neural network with long short-term memory architecture
by Viet Quoc Huynh; Hoang-Thuy-Tien Vo; Thu Anh Nguyen; Tuan Van Huynh
International Journal of Medical Engineering and Informatics (IJMEI), Vol. 15, No. 3, 2023

Abstract: This research attempts to use the electroencephalography signals based on physiological signals extracted from the database for emotion analysis to classify the emotion of the subjects by using classifier neural network algorithms. In this work, two types of neural network including 3D convolution neural network and hybrid network (3D convolution neural network model combined with long short-term memory architecture) were applied to train and test its ability of emotion states classification. As a result, the hybrid network gave the most efficient classification with an accuracy of around 80%, which was better than other algorithms such as support vector machine, random forest, convolution neural network. Furthermore, the results also showed that the accuracy achieved differently at various frequency bands, in which delta frequency band gave the highest accuracy. Combining signals of different frequencies helped to improve the classification efficiency.

Online publication date: Thu, 04-May-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Medical Engineering and Informatics (IJMEI):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com