Emotion recognition based on visual evoked EEG

Jiachen Hu Hu; Xuebin Qin Qin; Peijiao Yang Yang

doi:10.1117/12.2640861

24 October 2022 Emotion recognition based on visual evoked EEG

Jiachen Hu Hu, Xuebin Qin Qin, Peijiao Yang Yang

Proceedings Volume 12289, International Conference on Intelligent Manufacturing and Industrial Automation (CIMIA 2022); 122890H (2022) https://doi.org/10.1117/12.2640861
Event: International Conference on Intelligent Manufacturing and Industrial Automation (CIMIA 2022), 2022, Kunming, China

Abstract

EEG signals are closely related to mood changes, and the study of EEG signals can accurately reflect the changes of human emotions. In this paper, EEG signals were classified and recognized. Video emotion inducing materials were selected to induce subjects to produce happy, neutral and sad emotions, and EEG signals were collected at the same time. Wavelet packet transform, power spectral density and approximate entropy features were extracted, and then emotion classification was carried out by using width learning classification method, and then the classification results were analyzed and compared. The results show that the performance of differential entropy in single feature classification is up to 78.3%, while the accuracy of differential entropy and wavelet packet transform for feature fusion is up to 81.5%.

Citation Download Citation

Jiachen Hu Hu, Xuebin Qin Qin, and Peijiao Yang Yang "Emotion recognition based on visual evoked EEG", Proc. SPIE 12289, International Conference on Intelligent Manufacturing and Industrial Automation (CIMIA 2022), 122890H (24 October 2022); https://doi.org/10.1117/12.2640861

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available