Identifying Stable Patterns over Time for Emotion Recognition from EEG

By Wei-Long Zheng, Jia-Yi Zhu, Bao-Liang Lu. IEEE Transactions on Affective Computing, 2016

880 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/6297042abe4b19cb26c45bca67189dbcae300909

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Experimental and Cognitive Psychology

Citations in the corpus

Transfer Learning for EEG-Based Brain–Computer Interfaces: A Review of Progress Made Since 2016 (2020, neutral): “[83] investigated whether stable EEG patterns exist over time for emotion recognition.”
EEG Based Emotion Recognition by Combining Functional Connectivity Network and Local Activations (2019, methodology): “, 68% for MAHNOB and 62% for DEAP) that is consistent with those reported in previous works [12] [26].”
Exploring EEG Features in Cross-Subject Emotion Recognition (2018, methodology): “Speciﬁcally, through evaluation over individual channels, we found that the channels with the best performances were mainly located in the bilateral temporal regions, which was consistent with the ﬁnding in Soleymani et al. (2012), Zheng et al. (2016).”
TSception: Capturing Temporal Dynamics and Spatial Asymmetry From EEG for Emotion Recognition (2021, background): “Zheng et al. [13] used a discriminative graph regularized extreme learning machine to investigate stable patterns over time from the differential entropy (DE) features of emotional EEG. Li et al. [14] utilized phase-locking value to construct emotion-related brain networks with multiple feature…”
EmotionMeter: A Multimodal Framework for Recognizing Human Emotions (2019, background): “However, the stability of emotion recognition systems has received very limited attention [51].”
Comparing Recognition Performance and Robustness of Multimodal Deep Learning Models for Multimodal Emotion Recognition (2021, methodology): “Besides, electroencephalography (EEG)-based emotion recognition has been demonstrated to be a reliable method because of its high recognition accuracy, objective evaluation and stable neural patterns [6], [7], [8], [9], [10].”
An Efficient LSTM Network for Emotion Recognition From Multichannel EEG Signals (2020, background): “Despite the popularity of subjectdependent models in EEG-based emotion recognition [19], [20], [21], some recent studies [22], [23], [24], [25], [26], [27], [28] suggest building models specially designed for subjectindependent evaluation.”
Multisource Transfer Learning for Cross-Subject EEG Emotion Recognition (2020, methodology): “Database “SEED” [7], [9], [38] was used in our experiments, where ﬁlm clips were used to evoke emotions.”
Multimodal and Temporal Perception of Audio-visual Cues for Emotion Recognition (2019, background): “However, the following audio time slices could provide valuable information [28].”
EEG Based Emotion Recognition: A Tutorial and Review (2022, methodology): “For SEED-VIG and both MI DE and logarithm PSD features were determined on in the range of ( 50 Hz) using a Hz a total of 50 y sub-bands, as shown in Table I. 2) Temporal Information Stream: of DE and logarithm PSD features extracted from each of the ws is , as presented in Table I. extracted feature”
A Review of Emotion Recognition Using Physiological Signals (2018, background): “In reference [25], the authors systematically evaluated the performance of six popular features: power spectral density (PSD), differential entropy (DE), differential asymmetry (DASM), rational asymmetry (RASM), asymmetry (ASM) and differential caudality (DCAU) features from EEG.”
EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization (2022, methodology): “…with machine learning methods like SVM [36], which ﬁrst achieved notable results on this dataset; graph regularized extreme learning machine (GELM) [40] with a single feed-forward layer to learn discriminative features, and regions to global spatial-temporal neural network (R2G-STNN) [42] that…”