Study on Driver Cross-Subject Emotion Recognition Based on Raw Multi-Channels EEG Data

被引:6
作者
Wang, Zhirong [1 ]
Chen, Ming [1 ]
Feng, Guofu [1 ]
机构
[1] Shanghai Ocean Univ, Sch Informat Sci, Shanghai 201306, Peoples R China
关键词
emotion recognition; multi-channels EEG; cross-subject; CNN; NETWORK;
D O I
10.3390/electronics12112359
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In our life, emotions often have a profound impact on human behavior, especially for drivers, as negative emotions can increase the risk of traffic accidents. As such, it is imperative to accurately discern the emotional states of drivers in order to preemptively address and mitigate any negative emotions that may otherwise manifest and compromise driving behavior. In contrast to many current studies that rely on complex and deep neural network models to achieve high accuracy, this research aims to explore the potential of achieving high recognition accuracy using shallow neural networks through restructuring the structure and dimensions of the data. In this study, we propose an end-to-end convolutional neural network (CNN) model called simply ameliorated CNN (SACNN) to address the issue of low accuracy in cross-subject emotion recognition. We extracted features and converted dimensions of EEG signals from the SEED dataset from the BCMI Laboratory to construct 62-dimensional data, and obtained the optimal model configuration through ablation experiments. To further improve recognition accuracy, we selected the top 10 channels with the highest accuracy by separately training the EEG data of each of the 62 channels. The results showed that the SACNN model achieved an accuracy of 88.16% based on raw cross-subject data, and an accuracy of 91.85% based on EEG channel data from the top 10 channels. In addition, we explored the impact of the position of the BN and dropout layers on the model through experiments, and found that a targeted shallow CNN model performed better than deeper and larger perceptual field CNN models. Furthermore, we discuss herein the future issues and challenges of driver emotion recognition in promising smart city applications.
引用
收藏
页数:13
相关论文
共 50 条
[41]   Cross-Subject EEG-Based Emotion Recognition Using Deep Metric Learning and Adversarial Training [J].
Alameer, Hawraa Razzaq Abed ;
Salehpour, Pedram ;
Hadi Aghdasi, Seyyed ;
Feizi-Derakhshi, Mohammad-Reza .
IEEE ACCESS, 2024, 12 :130241-130252
[42]   Learning a robust unified domain adaptation framework for cross-subject EEG-based emotion recognition [J].
Jimenez-Guarneros, Magdiel ;
Fuentes-Pineda, Gibran .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 86
[43]   Generator-based Domain Adaptation Method with Knowledge Free for Cross-subject EEG Emotion Recognition [J].
Dongmin Huang ;
Sijin Zhou ;
Dazhi Jiang .
Cognitive Computation, 2022, 14 :1316-1327
[44]   Cross-subject EEG-based emotion recognition through dynamic optimization of random forest with sparrow search algorithm [J].
Zhang X. ;
Wang S. ;
Xu K. ;
Zhao R. ;
She Y. .
Mathematical Biosciences and Engineering, 2024, 21 (03) :4779-4800
[45]   Personal-Zscore: Eliminating Individual Difference for EEG-Based Cross-Subject Emotion Recognition [J].
Chen, Huayu ;
Sun, Shuting ;
Li, Jianxiu ;
Yu, Ruilan ;
Li, Nan ;
Li, Xiaowei ;
Hu, Bin .
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2023, 14 (03) :2077-2088
[46]   Cross-Subject EEG-Based Emotion Recognition via Semisupervised Multisource Joint Distribution Adaptation [J].
Jimenez-Guarneros, Magdiel ;
Fuentes-Pineda, Gibran .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2023, 72
[47]   Enhancing cross-subject EEG emotion recognition through multi-source manifold metric transfer learning [J].
Shi X. ;
She Q. ;
Fang F. ;
Meng M. ;
Tan T. ;
Zhang Y. .
Computers in Biology and Medicine, 2024, 174
[48]   Enhancing cross-subject emotion recognition precision through unimodal EEG: a novel emotion preceptor model [J].
Dong, Yihang ;
Jing, Changhong ;
Mahmud, Mufti ;
Ng, Michael Kwok-Po ;
Wang, Shuqiang .
BRAIN INFORMATICS, 2024, 11 (01)
[49]   Cross-subject and Cross-gender Emotion Classification from EEG [J].
Zhu, Jia-Yi ;
Zheng, Wei-Long ;
Lu, Bao-Liang .
WORLD CONGRESS ON MEDICAL PHYSICS AND BIOMEDICAL ENGINEERING, 2015, VOLS 1 AND 2, 2015, 51 :1188-1191
[50]   Easy Domain Adaptation for cross-subject multi-view emotion recognition [J].
Chen, Chuangquan ;
Vong, Chi-Man ;
Wang, Shitong ;
Wang, Hongtao ;
Pang, Miaoqi .
KNOWLEDGE-BASED SYSTEMS, 2022, 239