EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training

Weiguo Zhang

doi:10.47297/taposatWSP2633-456921.20260704

PDF
导出
分享
收藏
专辑

EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training

7卷第4期

浏览量: 0 Downloads: 0

EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training
EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training
School of Artificial Intelligence, Zhejiang Dongfang Polytechnic, Wenzhou, Zhejiang, 325000. China
2026年7卷第4期页码：116-119
纸质出版：2026-04-30
DOI：10.47297/taposatWSP2633-456921.20260704
Accepted：

Scan QR Code

Weiguo Zhang. (2026). EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training. 科技理论与实践（英文版）, 7(4), 116-119.

Zhang Weiguo.EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training[J].Theory and Practice of Science and Technology,2026,07(04):116-119.
Weiguo Zhang. (2026). EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training. 科技理论与实践（英文版）, 7(4), 116-119. DOI： 10.47297/taposatWSP2633-456921.20260704.

Zhang Weiguo.EEG Emotion Recognition Using Multi-Feature DNN with PCA and Multi-Seed Training[J].Theory and Practice of Science and Technology,2026,07(04):116-119. DOI： 10.47297/taposatWSP2633-456921.20260704.

摘要

Abstract

EEG-based emotion recognition is crucial for affective computing and human-computer interaction. This study proposes a deep neural network framework using multi-domain statistical features—including mean

variance

standard deviation

kurtosis

skewness

and zero-crossing rate—combined with PCA for dimensionality reduction and multi-seed training for robustness. Evaluated on a 32-channel EEG dataset

the model achieved an average accuracy of 76.31% across three runs

with a peak accuracy of 77.49%. The approach demonstrates reliable and generalizable performance

providing a practical solution for real-world EEG emotion recognition applications.

关键词

Keywords

references

Z. Xie, Y. Chen, and J. Guo, "EEG-based emotion recognition using CNN+LSTM hybrid neural model," J. Chengdu Univ. Inf. Technol., vol. 41 , no. 2 , pp. 147 – 161 , 2026 .

L. Ren and J. Sun, "EEG emotion classification based on CNN and LSTM," J. Changchun Univ., vol. 35 , no. 8 , pp. 13 – 27 , 2025 .

R. Zeng, S. Bai, S. Zhang, and L. Chen, "EEG-based emotion recognition using convolutional neural networks," East China Univ. J. Inf. Sci. Eng., pp. 1 – 10 , 2026 .

Y. Cao, "Multidimensional fusion emotion recognition model based on EEG signals," Tech. Autom. Appl., vol. 45 , no. 3 , pp. 99 – 103 , 2026 .

X. Xu, J. Li, Y. Lu, Y. Tian, X. Wang, and Z. Liu, "A review of research on emotion recognition using EEG signals," Shanxi Electron. Technol., vol. 2 , no. 245 , pp. 119 – 123 , 2026 .

A. Koelstra, et al., "DEAP: A database for emotion analysis using physiological signals," IEEE Trans. Affect. Comput., vol. 3 , no. 1 , pp. 18 – 31 , 2012 .

S. Li and M. Lu, "Emotion classification based on EEG signals using wavelet transform and SVM," Neurocomputing, vol. 100 , pp. 53 – 63 , 2013 .

J. Zhang, et al., "EEG-based emotion recognition using differential entropy features," IEEE Trans. Cybern., vol. 46 , no. 1 , pp. 282 – 293 , 2016 .

H. Ko, S. Nam, and H. Lee, "Time-domain feature extraction for EEG-based emotion recognition," Sensors, vol. 18 , no. 7 , pp. 1 – 15 , 2018 .

X. Li, Y. Zhang, and W. Chen, "EEG emotion recognition using LSTM with attention mechanism," Comput. Biol. Med., vol. 118 , pp. 103642 , 2020 .

文章被引用时，请邮件提醒。

Submit

Artificial Intelligence for Facial Emotion Recognition: A Review

Optimization of Lightweight Convolutional Neural Networks for Pedestrian Recognition

Research on the Living Transmission of Intangible Cultural Heritage from the Perspective of Digital Preservation

Generative AI-driven robo-advisors: Technological Evolution, Risk Mechanisms and Collaborative Governance Pathways

Construction and Application of Coastline Erosion Risk Prevention and Control System Based on Ecological Engineering

Related Author

Waikan Chong Intelligent Science and Engineering, Jinan University

Kaifu Dai

Related Institution

Intelligent Science and Engineering, Jinan University

School of Computer and Information Technology, Hohai University

⁰