Identifying Stable Patterns over Time for Emotion Recognition from EEG

被引:650
作者
Zheng, Wei-Long [1 ,2 ]
Zhu, Jia-Yi [1 ,2 ]
Lu, Bao-Liang [1 ,2 ]
机构
[1] Shanghai Jiao Tong Univ, Ctr Brain Comp & Machine Intelligence, Dept Comp Sci & Engn,Key Lab, Shanghai Educ Commiss Intelligent Interact & Cog, 800 Dong Chuan Rd, Shanghai 200240, Peoples R China
[2] Shanghai Jiao Tong Univ, Brain Sci & Technol Res Ctr, 800 Dong Chuan Rd, Shanghai 200240, Peoples R China
基金
中国国家自然科学基金;
关键词
Affective computing; affective brain-computer interaction; emotion recognition; EEG; stable EEG patterns; machine learning; extreme learning machine; EXTREME LEARNING-MACHINE; TEST-RETEST RELIABILITY; MUSIC; RESPONSES; OSCILLATIONS; ASYMMETRY; SELECTION; STIMULI;
D O I
10.1109/TAFFC.2017.2712143
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
In this paper, we investigate stable patterns of electroencephalogram (EEG) over time for emotion recognition using a machine learning approach. Up to now, various findings of activated patterns associated with different emotions have been reported. However, their stability over time has not been fully investigated yet. In this paper, we focus on identifying EEG stability in emotion recognition. We systematically evaluate the performance of various popular feature extraction, feature selection, feature smoothing and pattern classification methods with the DEAP dataset and a newly developed dataset called SEED for this study. Discriminative Graph regularized Extreme Learning Machine with differential entropy features achieves the best average accuracies of 69.67 and 91.07 percent on the DEAP and SEED datasets, respectively. The experimental results indicate that stable patterns exhibit consistency across sessions; the lateral temporal areas activate more for positive emotions than negative emotions in beta and gamma bands; the neural patterns of neutral emotions have higher alpha responses at parietal and occipital sites; and for negative emotions, the neural patterns have significant higher delta responses at parietal and occipital sites and higher gamma responses at prefrontal sites. The performance of our emotion recognition models shows that the neural patterns are relatively stable within and between sessions.
引用
收藏
页码:417 / 429
页数:13
相关论文
共 66 条
[41]
Murugappan Murugappan, 2010, Journal of Biomedical Science & Engineering, V3, P390, DOI 10.4236/jbise.2010.34054
[42]
Nie D, 2011, I IEEE EMBS C NEUR E, P667, DOI 10.1109/NER.2011.5910636
[43]
Nijboer F., 2009, Affective Computing and Intelligent Interaction and Workshops, P1, DOI DOI 10.1109/ACII.2009.5349479
[44]
Oliveira E.D. S. G., 2014, Em Information Systems and Technologies (CISTI), 2014 9th Iberian Conference on, P1
[45]
A Survey on Transfer Learning [J].
Pan, Sinno Jialin ;
Yang, Qiang .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2010, 22 (10) :1345-1359
[46]
Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy [J].
Peng, HC ;
Long, FH ;
Ding, C .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (08) :1226-1238
[47]
Discriminative graph regularized extreme learning machine and its application to face recognition [J].
Peng, Yong ;
Wang, Suhang ;
Long, Xianzhong ;
Lu, Bao-Liang .
NEUROCOMPUTING, 2015, 149 :340-353
[48]
A Novel Emotion Elicitation Index Using Frontal Brain Asymmetry for Enhanced EEG-Based Emotion Recognition [J].
Petrantonakis, Panagiotis C. ;
Hadjileontiadis, Leontios J. .
IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 2011, 15 (05) :737-746
[49]
INDUCING AND ASSESSING DIFFERENTIATED EMOTION-FEELING STATES IN THE LABORATORY [J].
PHILIPPOT, P .
COGNITION & EMOTION, 1993, 7 (02) :171-193
[50]
EEG ALPHA-ACTIVITY REFLECTS ATTENTIONAL DEMANDS, AND BETA-ACTIVITY REFLECTS EMOTIONAL AND COGNITIVE-PROCESSES [J].
RAY, WJ ;
COLE, HW .
SCIENCE, 1985, 228 (4700) :750-752